video_id
stringlengths
8
11
video
stringlengths
22
25
conversations
listlengths
2
2
seed46_2436
videos/HRA_part2/2436.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]" }, { "from": "gpt", "value": "Bad. The meerkat's claws in the video have generation issues, and the tail is malformed." } ]
seed46_106
videos/HRA_part2/106.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, wearing a white lab coat and stethoscope, stands in a lush green forest. A small mongoose, known for its agility, leaps playfully from the doctor's right shoulder to a branch above, capturing the essence of unexpected interactions in nature. The doctor looks on with a mix of surprise and delight, highlighting the unique connection between humans and wildlife. The vibrant green foliage and dappled sunlight create a serene atmosphere, emphasizing the peaceful coexistence between the medical professional and the nimble creature.]" }, { "from": "gpt", "value": "Bad. The animals in the video are distorted, and the characters' hands are twisted." } ]
seed42_2522
videos/HRA_part0/2522.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted jaguar leaps powerfully across a shallow stream, its body mid-air, muscles taut and rippling beneath golden fur flecked with black rosettes. The big cat's mouth is open slightly, revealing sharp canines, and its intense gaze is fixed forward. The water shimmers under the jungle canopy, splashing up droplets that freeze in the air around the airborne predator. The scene is captured in high-definition, focusing on the jaguar's dynamic movement and the surrounding lush vegetation, creating a vivid snapshot of the animal's natural habitat.]" }, { "from": "gpt", "value": "Bad. The video shows the jaguar walking with uncoordinated movements." } ]
seed44_2701
videos/HRA_part1/2701.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2315
videos/HRA_part1/2315.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, king of the beasts, is seen in the early morning, wiping its face with its paw in the grasslands of Africa. The lion, with a full, tawny mane, is lying down, using its right paw to wipe its face, perhaps after a recent meal or simply as a grooming habit. The grassy savanna stretches out behind it, dotted with acacia trees, providing a natural habitat for this powerful creature. The sun, still low in the sky, casts a warm glow over the scene, highlighting the lion's golden fur and the textures of the grass.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1256
videos/HRA_part0/1256.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, a writer, presumably the main character, runs along a sandy path at a luxurious resort, set against a backdrop of lush greenery and palm trees. Dressed in a gray tank top, black shorts, and black running shoes, he wears a determined expression as he focuses ahead. Accompanying him is a black jackal, resembling a wild dog, which runs alongside him, adding a sense of companionship and adventure to the narrative. The resort's opulent buildings and facilities are visible in the background, highlighting the contrast between nature and luxury.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2410
videos/HRA_part1/2410.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a brown jacket over his white medical coat, shovels snow from the sidewalk outside his clinic on a cold winter day. His attire includes dark pants, brown boots, and a brown cap, providing contrast against the snow-covered landscape. He pauses to wipe his brow, revealing a sense of effort, before continuing to clear the path, demonstrating his commitment to his patients. Behind him, the clinic's sign is visible, adding context to the scene. Throughout, the focus remains on the doctor's actions and the snowy environment, highlighting his dedication amidst the wintry conditions.]" }, { "from": "gpt", "value": "Bad. The doctor mentioned in the caption wearing a brown hat does not appear in the video." } ]
seed46_1498
videos/HRA_part2/1498.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single zebra, its distinctive black and white stripes gleaming under the golden savanna sun, is sprinting across a vast, grassy plain. The muscles in its legs are taut, demonstrating raw power and grace as it leaps over tufts of grass. The zebra's mane flutters in the wind, adding to the sense of motion and freedom. Dust kicks up from the zebra's hooves as it races, highlighting the speed and agility of this magnificent creature. Behind the zebra, the landscape stretches to a distant horizon, dotted with acacia trees and the faint outlines of other wildlife, providing context for the zebra's natural habitat.]" }, { "from": "gpt", "value": "Bad. The zebra's limbs in the video are incomplete during the running process." } ]
seed42_1899
videos/HRA_part0/1899.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown bear, standing on its hind legs on a wooden stage, wears a red and gold traditional Russian costume, complete with a matching hat. The bear, seemingly performing for an unseen audience, dances energetically to lively music, swaying its body and moving its paws in time with the beat. The stage is decorated with colorful banners and twinkling lights, creating a festive atmosphere, while the bear's expressive face conveys a sense of playful enjoyment in its unusual dance performance.]" }, { "from": "gpt", "value": "Normal. The fingers of the brown bear in the video were not generated, the body was distorted, and the facial features were blurry." } ]
seed46_1953
videos/HRA_part2/1953.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]" }, { "from": "gpt", "value": "Bad. The video does not show the koala wearing a small backpack as mentioned in the caption." } ]
seed46_1985
videos/HRA_part2/1985.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing swimming trunks and a smile, playfully interacts with a confident brown cat on the edge of a turquoise pool, its paws dipping into the water. The man gently splashes the cat, who responds with curiosity, showcasing their unique bond. The scene is set against a sunny, clear sky, with lush greenery in the background, highlighting the tranquility of the moment. The cat, comfortable and engaged, demonstrates its unusual fondness for water, while the man enjoys this special connection with his feline companion.]" }, { "from": "gpt", "value": "Normal. The man's movements in the video are basically normal, with slight disharmony; the cat's movements are not smooth and coordinated, with sudden changes." } ]
seed42_1860
videos/HRA_part0/1860.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, sun-dappled forest, a small, bushy-tailed squirrel gently caresses a smooth, brown egg nestled among vibrant green moss on a flat rock. The squirrel, with its soft, gray fur and alert eyes, tenderly touches the egg with its tiny paws, creating a heartwarming scene of unexpected care. The lush surroundings include tall trees, filtered sunlight, and a variety of foliage, adding depth and texture to the intimate moment shared between the squirrel and the fragile egg.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2962
videos/HRA_part2/2962.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male worker, wearing a gray T-shirt with a logo, blue jeans, and a dark cap, assembles furniture in a bright room. He focuses on tightening screws on a wooden dresser using a cordless drill, demonstrating his expertise. The room is filled with natural light, illuminating the task at hand. Moments later, he expertly aligns the dresser drawers, ensuring they fit perfectly. Lastly, he stands back to admire his completed work, a fully assembled dresser standing against a white wall, with the sunlight highlighting the wood grain and the worker's satisfaction in his craftsmanship.]" }, { "from": "gpt", "value": "Bad. The video shows the male worker using a cordless drill, but his movements are not very continuous and fluid, showing some lack of coordination." } ]
seed42_3172
videos/HRA_part0/3172.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a navy suit with a crisp white shirt and a patterned tie, sits at an opulent wooden desk. The room is richly decorated with leather-bound books and classic art pieces. He lifts a fork filled with a gourmet meal to his mouth, savoring each bite. The table is set with fine china and silverware, a half-empty glass of red wine standing beside a nearly finished plate of food, indicating a moment of leisure in his busy schedule. Soft ambient light from a nearby lamp illuminates the scene, casting warm shadows across the polished wood surface.]" }, { "from": "gpt", "value": "Normal. The character's action of eating in the video is slightly unsmooth." } ]
seed44_3095
videos/HRA_part1/3095.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young woman wearing a yellow top and blue jeans is attentively cleaning a large, rectangular fish tank. She is seen smiling while scrubbing the glass with a sponge, ensuring a clear view of the colorful fish and underwater plants inside. The tank is illuminated by overhead lights, highlighting the woman's focused efforts. Her movements are gentle yet thorough, maintaining the aquatic environment's health and beauty. Throughout the process, the fish swim calmly around her, undisturbed by her presence, as she works diligently to keep their home pristine.]" }, { "from": "gpt", "value": "Bad. The woman's arms deform while wiping the glass, and her hands appear deformed." } ]
seed42_1472
videos/HRA_part0/1472.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat and blue latex gloves, gently wipes a small, injured hedgehog with a cotton swab soaked in antiseptic solution, under the soft glow of an examination lamp. The hedgehog, nestled in a bed of green leaves, remains calm throughout the procedure, as the veterinarian carefully cleans its quills and skin. The scene is set in a cozy, well-lit clinic room filled with medical equipment and supplies, emphasizing the tender care provided to the tiny patient.]" }, { "from": "gpt", "value": "Normal. The movements are a bit discontinuous." } ]
seed46_2748
videos/HRA_part2/2748.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a rustic vineyard setting, a young female cashier, dressed in a red apron over a white blouse, diligently wipes down the wooden counter of the quaint tasting room. Sunlight streams in through large windows, highlighting the rich textures of the wood and the lush greenery outside. The atmosphere is peaceful and inviting, with the sound of gentle music playing in the background and the distant hum of vineyard activities. The cashier's focused demeanor and meticulous cleaning convey a sense of pride in her work and the establishment, creating a welcoming environment for visitors.]" }, { "from": "gpt", "value": "Normal. The cashier's movements in the video are basically normal, with slight awkwardness." } ]
seed42_2603
videos/HRA_part0/2603.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1129
videos/HRA_part2/1129.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1190
videos/HRA_part2/1190.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket setting, a middle-aged janitor, clad in a green vest and holding a mop, finds himself unexpectedly chasing after a mischievous weasel. The weasel, sporting a tiny red cap, races down the aisles filled with neatly stacked produce and canned goods, causing mild chaos. The janitor, with a look of determined amusement, sprints behind, weaving through shoppers and dodging displays. Amidst the commotion, the supermarket's bright lights and colorful signage create a dynamic backdrop for this unusual pursuit.]" }, { "from": "gpt", "value": "Bad. The character's movements are not smooth, and the weasel's movements are not smooth." } ]
seed44_191
videos/HRA_part1/191.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, cosmic setting, a cashier, clad in a unique space suit adorned with symbols of diplomacy, traverses the mammoth hall of an intergalactic embassy. She walks with purpose, passing through a grand archway, her eyes set on a distant goal. Behind her, a massive window reveals the breathtaking expanse of stars and galaxies, highlighting the enormity of her mission among the celestial bodies. Her every step echoes in the spacious corridor, resonating with the gravity of her role in maintaining galactic peace.]" }, { "from": "gpt", "value": "Bad. The video did not generate the cashier or the distant goal." } ]
seed44_2178
videos/HRA_part1/2178.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown, shoulder-length hair unloads a stainless steel dishwasher in a modern kitchen with white cabinets and marble countertops. She wears a simple white T-shirt, blue jeans, and an apron, and her glasses rest on the tip of her nose as she intently organizes the dishes. The room is bright, with sunlight streaming in from a nearby window, illuminating the space and casting a warm glow on the polished floor. As she works, her movements are efficient and practiced, demonstrating her familiarity with the task.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_3040
videos/HRA_part0/3040.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1191
videos/HRA_part0/1191.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic tiger, with vibrant orange fur and distinctive black stripes, leaps from one of Pluto's icy mountains to another, demonstrating incredible agility against the backdrop of a dark, starry sky. The tiger's muscular physique and fierce facial expression are accentuated by the stark contrast between its warm coloring and the cold, icy terrain. The distant mountains, also made of ice, add depth to the scene, while the tiger's powerful leap captures the essence of strength and grace in motion.]" }, { "from": "gpt", "value": "Normal. The tiger's movements in the video are not smooth." } ]
seed44_2384
videos/HRA_part1/2384.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman named Martin, donning a black blazer over a gray turtleneck, sits in a high-end bar with wooden accents and modern light fixtures. He looks thoughtfully into the distance with a slight smile, holding a glass of whiskey, embodying a sense of sophistication and mystery. The bar, featuring plush red seats and a vibrant atmosphere, provides a contrast to Martin's introspective demeanor, highlighting his unique presence among the lively crowd.]" }, { "from": "gpt", "value": "Normal. The man in the video is basically normal, but there are slightly uncoordinated movements." } ]
seed46_1285
videos/HRA_part2/1285.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical, imaginative scene, a group of koalas dressed in miniature black suits and top hats gather under a starlit sky, paying respects at a unique space-themed funeral. One koala, standing out from the crowd, begins to dance sorrowfully yet gracefully, its movements illuminated by the glow of distant galaxies and shimmering stars. As it twirls, a cosmic dust trail follows its path, symbolizing the connection between life, death, and the vastness of the universe, creating a surreal and poignant moment in the vast expanse of space.]" }, { "from": "gpt", "value": "Normal. No top hat was generated." } ]
seed46_1234
videos/HRA_part2/1234.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a stylish gray jacket, a black turtleneck, and dark jeans, stands against a backdrop of city lights and a bridge, exuding confidence. He is captured in various poses, first looking directly at the viewer with a serious expression, then showing a side profile with a contemplative look. Jay then smiles warmly, showcasing his friendly demeanor, before striking a cool pose with his hands in his pockets, gazing into the distance. Throughout, the urban landscape behind him complements his modern style and enigmatic persona.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2309
videos/HRA_part1/2309.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with glasses and a neatly trimmed beard, wearing a dark green collared shirt, focuses intently on fixing a leaky faucet in a public restroom. The faucet is positioned above a stainless steel sink with a mirror in the background. The janitor kneels on a yellow floor mat, using a wrench from his well-stocked tool belt to tighten the faucet's handle. The scene is illuminated by overhead fluorescent lights, casting a warm glow on the janitor's determined face as he works diligently to stop the dripping water.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed42_1630
videos/HRA_part0/1630.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, passionate writer in a vibrant red dress is captured in a series of captivating moments, all set within the lush, golden ambiance of an orchard during autumn. She begins by standing pensively, holding a vintage typewriter, embodying creativity and inspiration. Next, she's shown mid-dance, arms elegantly extended, her movements expressive and free, the typewriter now resting on the ground, symbolizing her liberation from constraints. In another scene, she leans back, laughing joyously, her feet slightly off the ground, the typewriter still visible, highlighting her uninhibited spirit. Lastly, she strikes a confident pose, hands on hips, with a serene smile, the typewriter by her side, signifying her connection to both art and nature. Throughout, the orchard's warm colors and abundant fruit provide a rich, textured setting for her expressive journey.]" }, { "from": "gpt", "value": "Bad. The woman in the video dances very unsmoothly, with uncoordinated movements." } ]
seed42_1387
videos/HRA_part0/1387.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black vest, finds himself dancing amidst towering trees in a dense forest. As he gracefully twirls, a majestic bison watches from the shadows, its powerful presence adding a touch of wildness to the surreal encounter. The forest, filled with lush greenery and dappled sunlight, provides a natural stage for this unexpected dance performance, where the lines between human and nature blur in a harmonious display.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1113
videos/HRA_part0/1113.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]" }, { "from": "gpt", "value": "Bad. The video shows the gray wolf with extra limbs, and the mouth is generated slightly larger." } ]
seed46_3112
videos/HRA_part2/3112.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious engineer, clad in a blue button-down shirt and khaki pants, kneels beside an indoor track designed for mice. The track, illuminated by overhead lights, features a small mouse energetically running within its confines. The engineer observes intently, notebook in hand, ready to record data from the experiment. Behind him, a lab coat hangs on a hook, and a shelf displays various scientific instruments and books, alluding to the academic setting. Throughout the scene, the mouse continues its steady pace on the track, under the watchful eye of the dedicated engineer.]" }, { "from": "gpt", "value": "Bad. The video shows a mouse running, but the movements are not continuous and smooth, there is a lack of coordination; the engineer holds a notebook to record experimental data, but the actions are not very clear and smooth, there is a lack of coordination." } ]
seed44_2701
videos/HRA_part1/2701.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]" }, { "from": "gpt", "value": "Bad. The meerkat and horse's head and limbs generation in the video have problems." } ]
seed46_3066
videos/HRA_part2/3066.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vibrant scene, a group of people wearing colorful swimsuits swim in a large, clear pool, with a majestic giraffe standing nearby, observing the swimmers with curiosity. Overhead, a futuristic Photon sail floats gracefully in the sky, reflecting sunlight and casting dynamic shadows onto the water below. The people interact with the giraffe gently, feeding it leaves, while the sail continues its serene journey across the sky, creating a harmonious blend of nature and advanced technology.]" }, { "from": "gpt", "value": "Bad. People's movements in the video are not smooth." } ]
seed42_1832
videos/HRA_part0/1832.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]" }, { "from": "gpt", "value": "Bad. The video did not generate the moose wearing an astronaut suit as mentioned in the caption." } ]
seed46_2043
videos/HRA_part2/2043.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket and dark pants, walks down a clean hallway illuminated by bright overhead lights, holding a small, active gerbil in a transparent plastic ball. The gerbil, running energetically on its wheel inside the ball, seems unfazed by the movement. The janitor navigates around a corner, continuing his journey with the gerbil in tow, the clean environment and well-lit corridor reflecting the diligence of his custodial duties.]" }, { "from": "gpt", "value": "Bad. The hamster's body is distorted, the character's face is distorted, and the hands are distorted." } ]
seed46_1175
videos/HRA_part2/1175.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, with short brown hair and a neatly trimmed beard, laughs wholeheartedly while sitting on a brown leather sofa. He wears a dark gray turtleneck sweater, black jeans, and a silver wristwatch, set against a warm-toned living room backdrop. The room features wooden floors, a large window with natural light, and a lush green plant, creating a cozy atmosphere. The actor's laughter is genuine and infectious, his eyes crinkling at the corners as he leans back on the couch, enjoying a private joke.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_1672
videos/HRA_part1/1672.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat, a dingo, wearing a small spacesuit, curiously explores the hydroponic garden, gently caressing the leaves of vibrant green plants under the glow of artificial lights designed to mimic sunlight. Nearby, an astronaut, clad in a full spacesuit, tenderly pets the dingo, creating a bond between man, animal, and the pioneering spirit of space agriculture, all against the backdrop of a vast, starlit universe visible through the habitat's clear dome.]" }, { "from": "gpt", "value": "Bad. The video does not show the dingo wearing a small spacesuit as mentioned in the caption." } ]
seed44_3207
videos/HRA_part1/3207.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mongoose, recognized by its sandy brown fur, black-tipped tail, and alert demeanor, runs swiftly across a dry, grassy terrain under a clear blue sky. It bounds gracefully over small tufts of grass, its body elongating and contracting with each leap, showcasing its agility and speed. Its eyes are focused ahead, ears perked, and nose twitching, indicating high alertness as it navigates the open space. The mongoose's movement is fluid and purposeful, its feet barely touching the ground as it darts forward, leaving a slight cloud of dust in its wake.]" }, { "from": "gpt", "value": "Bad. The meerkat in the video is abnormally distorted." } ]
seed42_2801
videos/HRA_part0/2801.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow vest and khaki pants, walks down a dimly lit hallway, pushing a red cleaning cart. Suddenly, a small brown mouse scurries across the floor, its movements quick and cautious. The janitor stops, observing the unexpected visitor with mild curiosity before continuing on his path, the mouse now hidden from view, leaving behind a sense of quiet solitude in the empty corridor.]" }, { "from": "gpt", "value": "Normal. The cleaner's hands and feet are generated blurry, and the small brown mouse is generated abnormally." } ]
seed46_2579
videos/HRA_part2/2579.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large herd of African buffalo, numbering in the hundreds, thunder across an expansive savanna, kicking up clouds of dust as they run. The buffaloes, with their distinctive large horns and sturdy bodies, move in unison, creating an awe-inspiring display of collective power and movement. The scene is set against a backdrop of distant acacia trees and a clear blue sky, emphasizing the vastness of the African wilderness. The herd's movement is so intense that it sends smaller animals scattering in all directions, highlighting the raw energy and strength of these magnificent creatures in motion.]" }, { "from": "gpt", "value": "Normal. The water buffalo's movement in the video is basically normal, but there is slight uncoordination." } ]
seed42_2882
videos/HRA_part0/2882.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A powerful lion, defying expectations, swims through a tranquil, crystal-clear lake, its muscular body moving gracefully beneath the water's surface. The big cat's tawny coat glistens as it propels itself forward with strong, deliberate strokes. Its piercing gaze remains fixed ahead, showcasing its innate strength and adaptability in an unexpected aquatic environment. The scene is set against a lush, verdant landscape, highlighting the unique and captivating behavior of this typically terrestrial predator.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2843
videos/HRA_part2/2843.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, clad in a navy-blue jacket adorned with badges and a matching hat, diligently shovels snow from the sidewalk in front of a modest, red-brick building. The scene is set in the early morning hours, as indicated by the dimly lit street and the absence of pedestrians. Snowflakes continue to fall gently from the gray sky, accumulating on the officer's shoulders and the brim of his hat. Despite the cold, he works with determination, clearing a path for safe passage, embodying the spirit of service and community. The shovel he uses is standard issue, with a sturdy wooden handle and a metal blade, further emphasizing the practical nature of his task.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2942
videos/HRA_part0/2942.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]" }, { "from": "gpt", "value": "Normal. The female rock climber's face generation is uncoordinated, and the arms are generated distorted." } ]
seed42_3182
videos/HRA_part0/3182.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male chef, wearing a clean white chef's jacket with short sleeves, meticulously polishes silverware in a well-lit kitchen. The utensils, which include forks, knives, and spoons, gleam under the bright lights as he works. Behind him, a large window reveals a bustling city skyline during daytime, adding a touch of urban sophistication to the scene. The chef's focused expression and the contrast between the shiny silverware and the white chef's jacket create a visually appealing composition.]" }, { "from": "gpt", "value": "Normal. The character's movements are not smooth." } ]
seed44_1832
videos/HRA_part1/1832.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]" }, { "from": "gpt", "value": "Bad. The adult moose's movements in the video are not smooth, and the astronaut's movements are also not smooth." } ]
seed44_1206
videos/HRA_part1/1206.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars gracefully through the crisp, blue sky, its powerful wings spread wide, casting a shadow on the rugged mountain terrain below. The eagle's piercing golden eyes scan the landscape intently, searching for prey. Its striking white head and tail feathers contrast vividly against the dark brown body, creating an awe-inspiring sight against the panoramic backdrop of snow-capped peaks and lush valleys. As it glides effortlessly, the wind ruffles its feathers, highlighting the intricate patterns and textures of its plumage, while the sun illuminates the scene, casting a warm glow on the breathtaking view.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2343
videos/HRA_part2/2343.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit prairie dotted with green shrubs and patches of tall grass, a large bison is rolling on its back in the dirt, surrounded by a cloud of dust. The bison, with its shaggy, brown fur and majestic horns, is enjoying a dust bath, rubbing vigorously against the ground. The camera captures the bison's content face as it lies on its side, legs kicking playfully in the air, creating a plume of dust that envelops its body. This behavior, known as 'dusting,' helps the bison remove parasites and excess oil from its coat, showcasing the creature's natural habits in a captivating scene.]" }, { "from": "gpt", "value": "Normal. The limbs of the buffalo in the video are incomplete." } ]
seed46_1472
videos/HRA_part2/1472.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat and blue latex gloves, gently wipes a small, injured hedgehog with a cotton swab soaked in antiseptic solution, under the soft glow of an examination lamp. The hedgehog, nestled in a bed of green leaves, remains calm throughout the procedure, as the veterinarian carefully cleans its quills and skin. The scene is set in a cozy, well-lit clinic room filled with medical equipment and supplies, emphasizing the tender care provided to the tiny patient.]" }, { "from": "gpt", "value": "Bad. The character's arm is twisted, the hand is distorted, and the hedgehog's face is contorted." } ]
seed42_2053
videos/HRA_part0/2053.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, futuristic space station, a diligent janitor, clad in a silver reflective suit, pushes a high-tech cleaning cart while walking down a long, sterile corridor illuminated by cool, artificial lights. Suddenly, the walkie-talkie on his belt crackles to life, transmitting a message from mission control regarding an incoming transmission from deep space. The janitor stops, listens intently, and acknowledges the message before continuing his duties, passing by a large window displaying the awe-inspiring view of distant galaxies and star clusters. Throughout the scene, a small Bobcat construction vehicle, equipped with advanced space-grade tools, can be seen in the background, autonomously performing maintenance tasks on the station's outer hull.]" }, { "from": "gpt", "value": "Normal. The person's arm is twisted, and the leg is twisted." } ]
seed44_1737
videos/HRA_part1/1737.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a brown jacket and khaki pants, sits on a wooden chair in a spacious, empty room with high ceilings and large windows, stitching a button onto his garment with a look of intense concentration. The button, which matches the color of his jacket, is being sewn back on with a strong thread, as the man holds the fabric taut with his free hand. The room is bathed in soft, natural light, casting gentle shadows across the floor and highlighting the dust motes that dance in the air. The janitor's face is set in a serious expression, his brow furrowed in determination as he carefully guides the needle through the fabric, ensuring the button is securely fastened. Behind him, a row of neatly arranged brooms and cleaning supplies stand against the wall, a testament to his hard work and dedication to keeping the space clean and orderly.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_3009
videos/HRA_part0/3009.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a police officer, clad in a high-tech suit with neon accents, runs across a rugged asteroid surface illuminated by the distant stars. The officer, equipped with a helmet and breathing apparatus, sprints past mining equipment and industrial structures, indicating an asteroid mining operation. With each stride, the officer's suit glows under the harsh lighting of the asteroid's environment, highlighting the action and determination in this dynamic scene set against the backdrop of space exploration and law enforcement.]" }, { "from": "gpt", "value": "Bad. The video clearly shows the officer running, but the movements are not very continuous and smooth, appearing uncoordinated." } ]
seed46_1393
videos/HRA_part2/1393.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a beige jacket, beige pants, and brown shoes, is seen in a close-up shot, wiping his face with a towel, looking exhausted yet determined. Behind him, a kangaroo, possibly a joeey given its smaller size, stands on the lush green grass of what appears to be a vast Australian outback, adding an element of surprise and quirkiness to the scene. The kangaroo's presence suggests an unusual encounter or storyline, while the actor's weary yet resolute demeanor hints at a challenging journey or performance.]" }, { "from": "gpt", "value": "Normal. The character's movements are not smooth." } ]
seed44_1201
videos/HRA_part1/1201.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A musician, dressed in a silver spacesuit, floats weightlessly in orbit around Earth, cradling a vibrant red electric guitar. His helmet visor reflects the stunning view of our planet, encapsulating the vastness of space. He gently caresses the guitar, playing it in zero gravity, as the blue and green hues of Earth contrast beautifully with the darkness of space behind him. The visual conveys a sense of tranquility and isolation, with the musician appearing lost in music amid the cosmic backdrop.]" }, { "from": "gpt", "value": "Normal. The musician's movements in the video are basically normal, with slight coordination issues." } ]
seed42_1682
videos/HRA_part0/1682.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, distinguished by its black and white striped face and gray fur, runs across a lush green meadow dotted with yellow flowers. The badger, with a serious expression, moves purposefully through the grassy landscape under a cloudy sky. It pauses briefly, standing upright on its hind legs, before continuing its run. Throughout the scene, the badger maintains its focus and direction, showcasing its agility and determination in the outdoors.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2975
videos/HRA_part0/2975.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a NASA jumpsuit walks alongside a curious, friendly bear in a space helmet, both exploring a futuristic space station designed for tourism. The station, filled with advanced technology and panoramic views of the cosmos, offers a unique blend of engineering marvels and extraterrestrial wildlife encounters. The engineer, equipped with tools and a tablet, ensures the safety and functionality of the space station's systems, while the bear, adorned with a custom spacesuit and helmet, roams freely, interacting with visitors and adding an unexpected touch of whimsy to the space tourism experience. Together, they navigate the corridors and observation decks, creating an unforgettable scene of human and animal adaptation to life beyond Earth's atmosphere.]" }, { "from": "gpt", "value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements." } ]
seed44_2071
videos/HRA_part1/2071.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown jacket, attentively wipes a gerbil, held gently in his hands, using a small towel, under the warm glow of studio lights. The gerbil, appearing relaxed and well-cared for, is nestled in the director's hands, which are meticulously cleaning it. The director's demeanor suggests a careful and nurturing approach to handling the small animal, creating a contrast between his authoritative role on set and this tender moment of care.]" }, { "from": "gpt", "value": "Normal. The director's action of wiping the hamster in the video is basically normal, but there is some lack of coordination." } ]
seed44_1002
videos/HRA_part1/1002.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A patient teacher, dressed in a khaki shirt and denim jeans, sits on a wooden pier with fishing gear, teaching a young student the art of fishing. The teacher demonstrates casting a line into a serene lake at sunset, the water reflecting the warm hues of twilight. The student, wearing a red cap and a green vest, attentively watches, holding a fishing rod, as the teacher guides them on the pier. The teacher then hands the student a small fish, caught during the lesson, fostering a connection between nature and learning. Throughout, the teacher wears a wide-brimmed hat and a yellow life jacket, while the student is dressed in a red baseball cap, a green fishing vest, and holds a child-sized fishing rod, both immersed in the peaceful act of fishing by the water's edge.]" }, { "from": "gpt", "value": "Bad. No teacher wearing a yellow life jacket or student holding a child-sized fishing rod was generated." } ]
seed42_2049
videos/HRA_part0/2049.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stylish woman in a black-and-white striped dress, reminiscent of a zebra's pattern, walks confidently down a busy city street. She carries a small black purse and wears black sunglasses, adding to her sophisticated appearance. The urban setting is filled with pedestrians and street vendors, providing a dynamic backdrop for her stroll. As she moves, the camera captures her from various angles, highlighting the fluidity of her walk and the attention she garners from passersby. Throughout the scene, she maintains her poise and elegance, embodying the spirit of a modern, independent woman.]" }, { "from": "gpt", "value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements." } ]
seed44_2500
videos/HRA_part1/2500.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a visually stunning scene, an ibex is depicted crawling across a rocky landscape, as if experiencing time dilation, where time appears to slow down from the perspective of an observer. The ibex, with its distinct curved horns, moves deliberately over the rugged terrain, emphasizing the surreal sensation of time distortion. The camera captures this unusual sight in high detail, highlighting the ibex's textured fur and the stark, rocky environment, creating a captivating juxtaposition between the animal's natural agility and the slowed-down, almost meditative pace of its movement.]" }, { "from": "gpt", "value": "Normal. The video shows the goat walking basically normally, but with slightly uncoordinated movements." } ]
seed46_1410
videos/HRA_part2/1410.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student wearing a green jacket and khaki pants explores a lush rainforest, observing a koala as it clings to a eucalyptus branch. Moments later, the student leaps over a small stream, demonstrating agility and enthusiasm for nature. Then, the koala is seen jumping from branch to branch, its plush fur glistening with dew, highlighting the playful nature of these marsupials in their natural habitat. Finally, the student sits on a mossy log, watching the koala munch on eucalyptus leaves, capturing the serene beauty of the rainforest and the peaceful coexistence between humans and wildlife.]" }, { "from": "gpt", "value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, the legs are twisted, the koala's arms are twisted, the claws are twisted, and the face is distorted." } ]
seed44_1584
videos/HRA_part1/1584.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a yellow high-visibility vest, blue jeans, and a gray shirt, dances with uninhibited joy in the vastness of a desert canyon. The landscape features towering red rock formations, lush greenery, and a distant mountain range under a clear blue sky. The janitor, holding a broom as if it were a dance partner, spins and twirls with abandon, embodying a spirit of freedom and happiness amidst the stark beauty of nature. As the camera pans out, the scale of the canyons becomes apparent, contrasting the figure of the dancing janitor against the immense natural surroundings.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2965
videos/HRA_part1/2965.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes, the man's limbs are somewhat uncoordinated while walking." } ]
seed44_2843
videos/HRA_part1/2843.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, clad in a navy-blue jacket adorned with badges and a matching hat, diligently shovels snow from the sidewalk in front of a modest, red-brick building. The scene is set in the early morning hours, as indicated by the dimly lit street and the absence of pedestrians. Snowflakes continue to fall gently from the gray sky, accumulating on the officer's shoulders and the brim of his hat. Despite the cold, he works with determination, clearing a path for safe passage, embodying the spirit of service and community. The shovel he uses is standard issue, with a sturdy wooden handle and a metal blade, further emphasizing the practical nature of his task.]" }, { "from": "gpt", "value": "Normal. The character's face and hands are distorted in the video." } ]
seed42_2788
videos/HRA_part0/2788.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_2444
videos/HRA_part0/2444.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with a round face, brown hair styled in a bun, and wearing a gray top is seen sitting alone, her eyes welling up with tears that stream down her cheeks. She looks lost in thought, her gaze distant, as she holds a tissue in her right hand. Moments later, she wipes away her tears with the tissue, her emotions visible in her expressive face. Then, she is captured in a close-up, her eyes closed, a tear rolling down her cheek, her lips slightly parted, as she seems to be taking a deep breath. Lastly, she looks directly at the camera, her eyes filled with unshed tears, her cheeks flushed, conveying a sense of vulnerability and strength in her emotional state.]" }, { "from": "gpt", "value": "Normal. The woman's eyes in the video have generation issues, and there are missing fingers." } ]
seed44_1619
videos/HRA_part1/1619.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]" }, { "from": "gpt", "value": "Nomal. The person in the video is not on the exterior of a modern office building." } ]
seed42_2964
videos/HRA_part0/2964.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]" }, { "from": "gpt", "value": "Bad. The female cashier's face, hands, and arms are distorted in the video." } ]
seed44_1876
videos/HRA_part1/1876.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, characterized by its bright green and yellow scales with blue highlights, swims near a coral reef, its beak-like mouth clearly visible as it forages for food among the colorful underwater landscape. The fish's unique appearance is accentuated by the clear turquoise water and the diverse marine life surrounding it, creating a captivating scene in the depths of the ocean.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_1228
videos/HRA_part1/1228.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary black rhinoceros, distinguished by its large body and dual horns, is seen in a natural habitat, wiping itself against a tree. The rhino, with its rugged skin and muscular build, rubs its side against the trunk, leaving visible marks on the bark. The action takes place in a lush environment, with green vegetation and tall trees surrounding the scene, highlighting the animal's interaction with its surroundings. The rhinoceros continues to lean into the tree, using it to scratch an unreachable spot, emphasizing the creature's natural behavior in its native environment.]" }, { "from": "gpt", "value": "Normal. The rhino's head is twisted, and the neck is twisted." } ]
seed46_1426
videos/HRA_part2/1426.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a white shirt, beige cardigan, and khaki pants, abandons his usual set to embark on a new project - painting a room. Surrounded by the tools of this different trade, including a paint can, roller, and painter's tape, he applies blue paint to the walls with precision and focus. His directorial experience is evident in the way he methodically transforms the space, bringing the same level of detail and vision to this task as he would to directing a scene. The room, filled with natural light, highlights the process as he adds color to the previously neutral walls.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2576
videos/HRA_part2/2576.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a casual outfit of a gray hoodie and blue jeans, diligently cleans a large window in a modern building, surrounded by other windows. The natural light from outside illuminates the space, casting a warm glow on the young cleaner. The scene is set in a minimalist room with white walls and hardwood floors, adding to the clean aesthetic. The student, with a focused look on their face, uses a squeegee and a bucket of soapy water to ensure every inch of the glass is spotless, reflecting their commitment to the task at hand.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2763
videos/HRA_part1/2763.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A curious brown monkey with a fluffy tail is seen swimming in a clear blue pool, its limbs energetically paddling through the water. It occasionally glances at the camera with a mischievous look, as if enjoying a playful moment. The monkey's facial features are expressive, conveying a sense of fun and adventure. Its body language suggests a relaxed and confident demeanor as it navigates the aquatic environment, demonstrating an unusual sight of a primate enjoying a swim.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1513
videos/HRA_part2/1513.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_298
videos/HRA_part0/298.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An enthusiastic engineer in a red shirt, beige vest, and khaki pants is seen in an amusement park, surrounded by roller coasters, with a Ferris wheel visible in the distance. He runs through the park with a map in hand, passing by various rides and attractions. The video captures him stopping briefly to study the map, before continuing his energetic jog through the lively environment, showcasing his passion for both engineering and the thrilling atmosphere of amusement parks.]" }, { "from": "gpt", "value": "Normal. The engineer's fingers in the video are deformed, and the face is generated blurry." } ]
seed42_2710
videos/HRA_part0/2710.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]" }, { "from": "gpt", "value": "Bad. Did not generate boots, the actor walks leisurely alongside a woolly mammoth, the number of actors is incorrect." } ]
seed44_2163
videos/HRA_part1/2163.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical wet forest, twin toddlers wearing colorful, waterproof overalls and wide-brimmed hats are crawling on a natural wooden log bridge, exploring their surroundings with wide-eyed curiosity. They crawl through a dense thicket of vibrant green foliage, their clothing bright against the earthy tones of the forest floor. The babies continue their adventure, crawling over a carpet of moss and fallen leaves, undeterred by the rugged terrain. Their journey concludes as they crawl towards a shaft of sunlight filtering through the dense canopy above, illuminating their path in the heart of the forest.]" }, { "from": "gpt", "value": "Bad. The person in the video has a twisted body, head, feet, legs, and arms." } ]
seed44_2891
videos/HRA_part1/2891.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a miniature giraffe, no taller than a foot, crawls slowly across the surface of a vast, cosmic solar sail, its fabric shimmering with ethereal light against the backdrop of a star-studded universe. The giraffe, with its distinctive pattern and gentle demeanor, moves deliberately, exploring the alien landscape as if it were a terrestrial savanna. The sail, stretched taut and capturing the rays of a distant sun, provides a mesmerizing contrast to the earthly creature traversing its surface, creating a dreamlike juxtaposition between the terrestrial and the celestial.]" }, { "from": "gpt", "value": "Bad. The giraffe's face in the video was not generated completely, and there are issues with the overall generation." } ]
seed44_2949
videos/HRA_part1/2949.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning full gear and a helmet, takes a break from his usual duties to engage in a surprising hobby: gardening. He carefully plants flowers in a small garden plot, surrounded by a wooden fence, with a bright red firetruck visible in the background. His gloved hands, typically used to handle hoses and axes, now delicately place marigolds into the soil. The juxtaposition of his robust firefighting attire and the delicate act of gardening creates a unique and compelling visual narrative.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_2957
videos/HRA_part0/2957.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret, with a brown and white coat, swims through clear, bubbling water, showing its unique swimming style with its head held high and nose just above the waterline. It uses its webbed feet to propel itself forward, highlighting its natural aquatic abilities. The water droplets glisten around it, and its determined face conveys a sense of joy and playfulness in its unusual swimming endeavor.]" }, { "from": "gpt", "value": "Normal. The ferret's head and paws in the video have generation issues, with the ferret's paws suddenly disappearing or appearing in the middle frames." } ]
seed46_2870
videos/HRA_part2/2870.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director wearing a beige jacket walks through a set resembling a forest, carrying a clapboard marked 'Quantum Leap.' He stops to observe a CGI-generated rhinoceros walking past him, its movements synchronized with the director's pace. The rhinoceros, rendered with high detail, appears to interact naturally with the forest environment, while the director watches intently, his expression conveying a mix of professionalism and wonder.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1158
videos/HRA_part0/1158.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant village nestled near a lush watering hole, a tall giraffe gracefully bends its neck to drink, its spots blending harmoniously with the African landscape. Nearby, village life unfolds, with women carrying water pots on their heads, children playing under the watchful gaze of elders, and men engaged in lively conversations. Suddenly, a group of young boys leap into the refreshing waters, their joyful splashes contrasting with the calm surroundings. The scene is completed by a close-up of a giraffe's face, its large eyes and curious expression capturing the essence of this serene environment.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes, and children appear in the water." } ]
seed44_1150
videos/HRA_part1/1150.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]" }, { "from": "gpt", "value": "Bad. The hamster's body deforms and mutates while performing actions, and sometimes abnormalities appear." } ]
seed42_2031
videos/HRA_part0/2031.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and helmet, sits on a vintage red fire engine, enjoying a hearty meal of spaghetti with meatballs from a white plastic plate balanced on his lap. The scene is set against the backdrop of a bustling fire station, with the garage doors open, revealing the interior where fellow firefighters are engaged in various activities, creating a vivid snapshot of life at the station. Despite the chaos around him, the firefighter finds a moment of respite, his face illuminated by the warm glow of the setting sun filtering through the open bay doors.]" }, { "from": "gpt", "value": "Normal. The character's face and hands are distorted in the video." } ]
seed42_1764
videos/HRA_part0/1764.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a sleek silver spacesuit adorned with patches, performs an energetic dance against the backdrop of a vast, star-filled universe. The scene opens with the actor floating gracefully in zero gravity, spinning and twirling with the joy of someone experiencing the wonder of space tourism. Their movements are fluid and expressive, conveying a sense of freedom and exhilaration. As the dance continues, the actor executes a series of dynamic leaps and poses, each one highlighting the unique challenges and opportunities of dancing in microgravity. The stars shimmer and galaxies glow in the distance, providing a breathtaking canvas for this cosmic performance. Throughout the video, the actor's face, visible through the clear visor of their helmet, radiates with delight, sharing the magic of space travel through the universal language of dance.]" }, { "from": "gpt", "value": "Bad. The actors' movements in the video are very unsmooth and uncoordinated." } ]
seed46_1918
videos/HRA_part2/1918.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a brown leather jacket and a gray beanie, sits at a wooden table in a rustic, dimly lit room. With a focused gaze, they caress the worn pages of a chaparral poetry book, their right hand gently touching the text as if feeling the essence of the words. The scene conveys a sense of reverence and connection to literature, with the writer's attire and the chaparral book adding depth to the narrative. The room's ambiance, characterized by wooden elements and soft lighting, enhances the intimate atmosphere as the writer's hand, adorned with a silver ring, lovingly glides over the book's pages.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are not smooth." } ]
seed42_2680
videos/HRA_part0/2680.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy kitchen with wooden cabinets and a checkered floor, two young children, a boy and a girl, both wearing playful animal-shaped hats, work together to load a modern, stainless steel dishwasher. The boy, donning a blue striped shirt, carefully places a large plate into the rack, while the girl, clad in a pink dress, adds smaller dishes beside it. The room is filled with natural light from a nearby window, casting warm, golden tones over the scene. As they continue their task, the siblings share a giggle, highlighting the joy in their shared responsibility.]" }, { "from": "gpt", "value": "Bad. The children's hands and utensils in the video have generation issues; the hands of the children suddenly distort or disappear and reappear in the middle frames." } ]
seed44_2837
videos/HRA_part1/2837.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars through a clear blue sky, its powerful wings stretched wide, casting a shadow on the rugged, rocky terrain below. It effortlessly glides over a dense forest, the sunlight glinting off its russet and white plumage, with a backdrop of lush green trees. The hawk then focuses intently, spotting prey from above, its piercing eyes and curved beak displaying its predatory nature. It finishes by perching regally atop a barren tree branch, surveying its domain with a fierce gaze, the wind gently ruffling its feathers.]" }, { "from": "gpt", "value": "Bad. The red-tailed hawk's claws are twisted, wings are twisted, and head is twisted." } ]
seed44_1821
videos/HRA_part1/1821.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2235
videos/HRA_part0/2235.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]" }, { "from": "gpt", "value": "Bad. The koala's movements in the video are not smooth." } ]
seed42_200
videos/HRA_part0/200.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single camel, distinguished by its brown fur and a patterned red, yellow, and green saddle, stands against a desert landscape under a clear blue sky. It begins to move rhythmically, swaying to an unseen beat, its large eyes gazing into the distance. Moments later, it raises its head proudly, its mouth open in a gesture that suggests a joyful call or song. Then, the camel continues its dance, gracefully moving its legs in time with the music, its body language conveying a sense of happiness and freedom in the vast, sandy expanse.]" }, { "from": "gpt", "value": "Normal. The camel's legs are missing in the video, and there are problems with the generation of the eyes and mouth." } ]
seed46_3111
videos/HRA_part2/3111.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a gray sweater and blue jeans, steps out from a charming cottage, holding a small trash bag. She walks purposefully down a stone path, surrounded by lush greenery and flowers, to reach a large wooden bin. The scene is set in the golden hour, with soft sunlight filtering through the trees, casting a warm glow on the idyllic setting. The writer pauses for a moment, looking contemplative, before depositing the trash bag into the bin. The peaceful atmosphere and natural beauty of the surroundings provide the perfect backdrop for her daily routine, offering a glimpse into the simple yet meaningful moments in the life of an artist.]" }, { "from": "gpt", "value": "Bad. The woman's face, hands, feet, and legs are distorted in the video." } ]
seed44_2505
videos/HRA_part1/2505.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing elephant, adorned with vibrant red and gold patterns on its body, stands on one leg with its trunk gracefully curved upwards, embodying a joyful dance move. Against a rich, textured green jungle backdrop, the elephant's eyes sparkle with delight, its large ears slightly flared, and its tusks gleaming in the sunlight. Accompanied by smaller elephants in the background, also decorated in red and gold, the scene radiates a festive atmosphere, capturing the essence of an elephantine dance party in the lush, verdant surroundings.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2550
videos/HRA_part1/2550.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow vest over a dark jacket and jeans, walks purposefully down a hospital corridor. The hall is lined with evenly spaced white doors and illuminated by overhead lights, casting a warm glow. The man holds a mop bucket in one hand, its handle adorned with a colorful cloth hanging loosely. He moves with determination, his work boots echoing softly on the linoleum floor, creating a sense of routine and responsibility in the clean, institutional environment.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_2811
videos/HRA_part2/2811.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a traditional conical hat and simple clothing, guides a strong water buffalo through a shallow, muddy waterway by holding onto its rope halter. The buffalo, with its large, curved horns and powerful body, crawls on its belly through the mire, demonstrating its strength and endurance. The farmer, with a focused look on his face, carefully navigates alongside the animal, highlighting the bond between man and beast in rural life. The scene takes place against the backdrop of lush green fields, emphasizing the agricultural setting.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_1800
videos/HRA_part1/1800.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]" }, { "from": "gpt", "value": "Bad. The squirrel's movements in the video are very unsmooth and uncoordinated." } ]
seed46_1346
videos/HRA_part2/1346.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1424
videos/HRA_part2/1424.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray jacket and khaki pants, unloads a large, industrial dishwasher in a busy school cafeteria during lunchtime. He wears yellow rubber gloves and a face mask, and carries a mop and bucket, indicating his role in maintaining cleanliness. The scene captures him pausing for a moment, holding a clean tray, with students visible in the background, emphasizing the bustling environment. The janitor then continues his task, placing trays on a metal shelf, demonstrating his routine duty amidst the lively atmosphere of the cafeteria.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1214
videos/HRA_part2/1214.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a hedgehog, adorned with miniature headphones and a tiny guitar strapped to its back, embarks on an adventurous journey across a lush, green backyard. It navigates through grassy terrains, darting between vibrant flowers and undergrowth with a sense of purpose. The hedgehog's spines glisten under the golden sunlight, adding a touch of magic to the scene. As it runs, the camera captures the hedgehog from various angles, highlighting its determination and the enchanting world it inhabits. The setting is reminiscent of a fairy tale garden, complete with a wooden fence in the background, framing the hedgehog's spirited escapade.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_2230
videos/HRA_part0/2230.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush green forest setting, a pair of beavers are seen intimately caressing each other, their brown fur glistening with moisture from the nearby river. The male beaver gently touches the female's face with his forepaw, a tender gesture of affection. They are surrounded by tall trees and vegetation, providing a natural and peaceful environment for their interaction. The female beaver responds with a soft look, her whiskers moving slightly as she nuzzles closer to him. This heartwarming scene captures the emotional bond between these two creatures, highlighting the beauty of wildlife relationships.]" }, { "from": "gpt", "value": "Normal. One of the beaver's paws is slightly deformed." } ]