video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
---|---|---|
seed46_1809
|
videos/HRA_part2/1809.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 space station orbiting Earth, a waiter clad in a sleek silver uniform gracefully floats, serving exotic dishes to the guests seated at a long, transparent table. The space station, designed with curved edges and illuminated panels, offers breathtaking views of the planet below. The waiter, equipped with magnetic boots to assist in crawling and maneuvering through zero gravity, carefully balances a tray filled with delicacies. As he crawls from one guest to another, the curvature of the space station's interior is visible, creating a unique dining experience among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The server in the video does not have any crawling actions."
}
] |
seed42_3034
|
videos/HRA_part0/3034.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 actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Normal. The actor's fingers and facial features in the video were generated abnormally."
}
] |
seed46_1831
|
videos/HRA_part2/1831.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 doctor, wearing a white lab coat and blue gloves, is seen wiping the nose of a friendly coyote who is sitting calmly on a checkered medical table. The room is brightly lit, with medical supplies neatly arranged on shelves in the background. The doctor's compassionate expression and the coyote's trusting demeanor create a heartwarming moment, highlighting an unusual yet tender interaction between human and wild animal in a clinical setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1740
|
videos/HRA_part1/1740.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 artist, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Normal. The artist's actions of kneading the clay in the video are basically normal, but there is some lack of coordination."
}
] |
seed46_1052
|
videos/HRA_part2/1052.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 vivid outdoor scene, three young children sprint across a vast, sunlit chaparral landscape, their movements captured in slow motion to emphasize their carefree joy. Dressed in a red shirt, blue shorts, and black shoes, one child leads the pack, arms outstretched like wings. Another child, wearing a yellow top, green shorts, and brown sandals, follows closely behind, laughing gleefully. Trailing just behind, a third child in a purple dress and pink sneakers completes the trio, their faces alight with excitement as they race beneath the clear blue sky. The chaparral vegetation, with its rugged shrubs and distant mountain backdrop, provides a natural, textured setting for their energetic play.]"
},
{
"from": "gpt",
"value": "Bad. The child's legs and arms have become deformed."
}
] |
seed42_2334
|
videos/HRA_part0/2334.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 teacher, dressed in a casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2971
|
videos/HRA_part0/2971.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 dramatic scene, a distinguished actor, with short brown hair and wearing a black leather jacket, gazes intently into the camera, his face reflecting awe and concern. Behind him, a massive explosion of a white hole illuminates the dark cosmos, its brilliant light casting an ethereal glow on his features. In the next frame, he gently caresses the cheek of another character, his touch conveying deep emotion and connection, set against the backdrop of the universe's raw power. The contrast between the intimate gesture and the cosmic event underscores the intensity of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2867
|
videos/HRA_part0/2867.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 futuristic worker, clad in a high-tech silver spacesuit and helmet, walks across the expansive surface of an enormous solar sail, which glimmers under the vivid light of a distant star. The sail, a vast expanse of shimmering material, stretches out behind the figure, capturing the celestial radiance. The worker, equipped with a portable tool kit attached to the suit, is seen moving purposefully along the sail's surface, conducting maintenance or inspection tasks in the vastness of space. The background is filled with the dark void of space, dotted with distant stars, emphasizing the isolation and grandeur of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The future worker in the video walks basically normally, but there is slight movement inconsistency."
}
] |
seed42_1807
|
videos/HRA_part0/1807.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 professional-looking woman, dressed in a dark blazer, white blouse, and black trousers, sits at a cluttered desk in her office, surrounded by bookshelves filled with law books. Despite the serious environment, she is knitting a vibrant red scarf with a look of concentration on her face, her hands moving deftly as she works on her craft. The room is illuminated by a desk lamp, casting a warm glow over the scene, and a window can be seen behind her, offering a glimpse of a city skyline at twilight.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3131
|
videos/HRA_part1/3131.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 police officer, wearing a navy uniform with badge and name tag, meticulously cleans a large aquarium filled with colorful fish and aquatic plants, set against a backdrop of a modern, minimalist interior. The officer, displaying a gentle side, carefully tends to the tank, ensuring the well-being of the marine life within. The aquarium, illuminated by overhead lights, showcases various species of fish swimming calmly, oblivious to the officer's presence. The room's clean lines and neutral tones contrast with the vibrant colors of the fish, creating a visually striking scene.]"
},
{
"from": "gpt",
"value": "Bad. The officer's hand in the video is deformed."
}
] |
seed46_1465
|
videos/HRA_part2/1465.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 cheerful teacher, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2021
|
videos/HRA_part0/2021.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 police officer, wearing a standard uniform with a badge, hat, and tactical vest, stands under a dimly lit streetlamp on a quiet, empty urban street at night. The officer's face is contorted in anguish, tears streaming down their cheeks, highlighting the emotional weight they carry. Their eyes are closed, and they're holding a tissue in one hand, indicating a moment of vulnerability amidst their duty. The scene conveys a powerful message about the human side of law enforcement, emphasizing the emotional toll it can take on those who serve.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's fingers were not fully generated, and the face was distorted."
}
] |
seed46_3180
|
videos/HRA_part2/3180.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 vivid orange tabby cat leaps across the gap between two weathered warehouse rooftops under an overcast sky, its hind legs pushing off a wooden crate. The cat lands gracefully on the adjacent rooftop, its green eyes alert, before bounding away toward a rusty metal water tower in the distance. The scene is set against a backdrop of urban decay, with broken windows and graffiti adorning the brick walls of the warehouses. As the cat jumps, it passes by a row of similar crates, adding to the industrial atmosphere of the setting.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the cat heading towards a rusty metal water tower."
}
] |
seed44_2720
|
videos/HRA_part1/2720.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 male doctor, wearing a white lab coat over casual attire, skillfully prepares dinner in a modern kitchen with stainless steel appliances and granite countertops. He expertly chops vegetables on a wooden cutting board, using a sharp chef's knife, while a pot simmers on the stove, releasing aromatic steam. The kitchen is illuminated by soft overhead lights, casting a warm glow over the scene. Behind him, a large window displays an urban skyline at twilight, adding a touch of sophistication to the domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2162
|
videos/HRA_part2/2162.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 vibrant, otherworldly setting reminiscent of a space opera, a majestic camel, adorned with ornate, futuristic gear, leaps gracefully over an array of alien flora. The backdrop features a bustling spaceport with neon-lit structures and a variety of extraterrestrial beings. The camel's rider wears a sleek, armored suit with glowing accents, embodying a daring space adventurer. The scene is filled with dynamic energy as the camel bounds through the air, showcasing its agility against the backdrop of a technologically advanced society engaged in a grand performance.]"
},
{
"from": "gpt",
"value": "Bad. The rider's limbs and face were not generated, the body was generated in a twisted manner, the camel's limbs were partially missing, and there were issues with the face generation."
}
] |
seed46_2660
|
videos/HRA_part2/2660.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 chimpanzee dressed in a miniature waiter's outfit, complete with a crisp white shirt, black vest, and bow tie, walks on its hind legs through a lush, green forest. It carries a small silver tray balanced on its right hand, adding to the whimsical scene. The chimp's expressive face, with furrowed brows and a slight smile, conveys a sense of playfulness and determination as it navigates the natural environment, surrounded by tall trees and dappled sunlight filtering through the leaves.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed46_1864
|
videos/HRA_part2/1864.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 in the vastness of space, looks alert and ready for action. Suddenly, a band of space pirates descends upon him, their ships equipped with menacing weaponry. The meerkat, wearing a makeshift spacesuit and brandishing a high-tech weapon, prepares to defend himself. In the next scene, the meerkat is seen wiping away debris from a fierce battle, his eyes scanning the horizon for any further threats. Despite the chaos, he remains vigilant and resourceful, a true survivor in the cosmic wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The suricate is distorted when it moves."
}
] |
seed42_1661
|
videos/HRA_part0/1661.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 whole, fresh Atlantic cod fish, with clear eyes and shiny skin, rests on a bed of ice. Its mouth is slightly open, and it has a small silver ring through its lip. The fish is surrounded by green herbs and lemon slices, adding a pop of color against the icy background. The camera captures the cod from various angles, highlighting its texture and freshness, perfect for culinary preparations. Throughout the video, the fish remains stationary on the ice, the camera's movement providing dynamic visuals.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2978
|
videos/HRA_part1/2978.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 animated, friendly-looking gray elephant with large ears and a smiling face walks through the halls of a futuristic space education center. The hallways are filled with interactive exhibits, including a large model of the solar system hanging from the ceiling. The elephant, wearing a small backpack, interacts with the exhibits, using its trunk to press buttons and explore the educational displays about planets, stars, and galaxies. Children in astronaut costumes look on in amazement as the elephant continues its journey through the center, learning about the wonders of space.]"
},
{
"from": "gpt",
"value": "Bad. The button that the elephant needs to press with its trunk, as mentioned in the caption, does not appear in the video."
}
] |
seed44_1469
|
videos/HRA_part1/1469.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 construction worker, clad in a yellow high-visibility jacket, blue jeans, and brown work boots, walks purposefully near a yellow Bobcat excavator, which is positioned on a building site filled with sand and dirt. The excavator boasts a wide bucket and sits on the sandy terrain of the lot, while the worker strides with determination, hard hat in hand, past the heavy machinery, embodying the industrious spirit of a bustling worksite.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, legs are deformed, and the wheels behind are warped."
}
] |
seed42_2387
|
videos/HRA_part0/2387.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, dressed in a vibrant yellow jacket and khaki shorts, walks along a dirt path near a watering hole, where a hippopotamus lazily wallows in the cool mud. In the distance, the Martian landscape unfolds, with its rusty red dunes and sparse vegetation silhouetted against a sunset painted in hues of violet and orange. The celestial event casts a warm glow over the scene, highlighting the unique juxtaposition of Earthly life and extraterrestrial beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_332
|
videos/HRA_part1/332.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 director, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Normal. The director's walking in the video is basically normal, but there is slight movement disharmony."
}
] |
seed46_1016
|
videos/HRA_part2/1016.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, wearing a yellow life jacket and a helmet, is seen swimming alongside a moose in a large, clear lake. Both are in the middle of the water body, surrounded by vast expanses of water. The woman, with her dark brown hair visible, looks up at the moose, which is also swimming, its head held high above the water. The moose, with its distinctive antlers, swims parallel to her, both seemingly enjoying the cool waters. Behind them, a lush forest with tall green trees stretches to the horizon, providing a serene and picturesque backdrop to this unusual scene of a woman and a moose swimming together.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face, the moose's head, and the hand showing from the water are generated abnormally; there is another hand showing from the water."
}
] |
seed42_1607
|
videos/HRA_part0/1607.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, open field under a clear blue sky, two young children, a boy and a girl, both wearing vibrant yellow raincoats, wide-brimmed hats, and boots, are seen walking together. They carry a large, reflective solar sail, its metallic surface shimmering in the sunlight. The sail, supported by a wooden frame they hold, catches the wind as they walk, propelling them forward playfully across the grassy landscape. Their joyful expressions and the sail's gentle movements create a whimsical scene, blending elements of childhood wonder with futuristic technology.]"
},
{
"from": "gpt",
"value": "Normal. The faces and hands of the children in the video are generated poorly."
}
] |
seed42_1887
|
videos/HRA_part0/1887.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 charismatic male chef, wearing a classic white chef's jacket and black pants, is filmed in a bustling, modern restaurant kitchen. He begins by seasoning a dish with a sprinkle of herbs, his hands moving with practiced ease. Next, he deftly flips a piece of seared salmon in a sizzling pan, the steam rising around him adding to the atmosphere. Then, he carefully arranges the cooked salmon on a plate, garnishing it with fresh greens and a drizzle of sauce. Lastly, he gives a satisfied nod, presenting the beautifully plated meal to the camera, the vibrant colors of the food contrasting with the stainless steel appliances in the background.]"
},
{
"from": "gpt",
"value": "Bad. The hand appears deformed, and the chef's spatula suddenly disappears and reappears. And a plate of salmon suddenly appears."
}
] |
seed44_2659
|
videos/HRA_part1/2659.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 quaint village setting under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's body is twisted, the head is twisted, the feet are twisted, the legs are twisted, the character's face is twisted, the hands are twisted, the legs are twisted."
}
] |
seed42_2529
|
videos/HRA_part0/2529.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 female cashier with brown hair pulled into a bun, wearing a red apron over a white collared shirt, serves customers at a grocery store checkout lane. Suddenly, her eyes well up with tears, and she begins to quietly cry, her face showing a mix of sadness and professionalism as she continues ringing up items. The scene highlights her emotional struggle, balancing work responsibilities with personal feelings, all under the fluorescent lights of the supermarket.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's movements in the video are not smooth."
}
] |
seed46_2803
|
videos/HRA_part2/2803.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 white lab coat over a blue button-up shirt and khaki pants, walks alongside a capybara on a leash in a lush, green park. The doctor, sporting a neatly trimmed beard and a friendly smile, interacts with the large rodent, which is calmly trotting beside him on the grass. They pass by a wooden bench under the shade of leafy trees, creating a unique and peaceful scene in an urban oasis. The capybara, known for its docile nature, seems comfortable in the presence of the doctor, who gently guides it with the leash, both enjoying a leisurely stroll in the verdant surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2213
|
videos/HRA_part0/2213.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 unique scene, a waiter wearing a black vest and white shirt gently caresses various plants in a subtropical shrubland. Surrounded by lush greenery and vibrant flowers, he tenderly touches the leaves, creating an unexpected connection between service and nature. The camera captures his delicate movements as he interacts with the environment, highlighting the peaceful coexistence of a professional figure in an unconventional natural setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1517
|
videos/HRA_part2/1517.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 charming hedgehog, adorned with a miniature top hat and a tiny bow tie, pirouettes gracefully on a wooden stage under the glow of a spotlight. The hedgehog's expressive eyes sparkle with joy as it twirls, its quills gently swaying to an unheard melody. The backdrop features a painted night sky, complete with twinkling stars and a crescent moon, adding a whimsical touch to the scene. The hedgehog continues its delightful dance, captivating the audience with its unexpected grace and charm, all set against the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's movements are not smooth."
}
] |
seed46_1893
|
videos/HRA_part2/1893.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 dimly lit, spacious room filled with smoke and vibrant lights, two individuals, a man in a dark green shirt and a woman in a black top, are dancing enthusiastically. Suddenly, they stop, looking startled as a beam of green light illuminates them. An alien creature, with large, expressive eyes and a smooth, gray skin tone, descends from above, capturing their attention. The extraterrestrial being, adorned with a metallic, futuristic outfit, lands gracefully beside them, prompting the humans to react with a mix of fear and curiosity. Despite the initial shock, the trio begins to move in unison, engaging in an otherworldly dance, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The man's and alien's dance moves are discontinuous, with abrupt changes in their movements."
}
] |
seed42_1991
|
videos/HRA_part0/1991.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 the heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Bad. The antelopes' heads and the limbs of the large antelope in the video are generated abnormally; when the large antelope jumps, its limbs become distorted and sometimes suddenly disappear or reappear."
}
] |
seed42_2904
|
videos/HRA_part0/2904.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 large bull moose, antlers wide and impressive, runs through a lush, green meadow under a clear blue sky, with a distant mountain range visible on the horizon. Its powerful legs propel it forward in a graceful gallop, kicking up small clouds of dust from the dry earth beneath its hooves. The moose's coat is a deep brown, nearly black, and its large body ripples with muscles as it bounds across the landscape, the embodiment of wild strength and freedom. In the background, tall trees frame the edges of the clearing, their leaves whispering softly in the breeze, while birds take flight, startled by the majestic creature's sudden movement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2560
|
videos/HRA_part1/2560.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 wearing a yellow high-visibility vest, khaki cargo shorts, and a green t-shirt is crawling on a sandy beach, possibly searching for lost items or performing an unusual cleaning task. The beach is wide and sandy, with shallow water and a calm sea stretching into the distance. Palm trees dot the landscape, and the beach is relatively empty except for a few people walking in the background. The janitor's actions are focused and deliberate, contrasting with the serene coastal scenery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2280
|
videos/HRA_part1/2280.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 young student, dressed in a gray sweater over a white collared shirt and khaki pants, sits at a desk in a classroom after hours. The room is illuminated by natural light from a large window, casting a warm glow over the scene. The student is focused on replacing batteries in a scientific calculator, an essential tool for their studies. They carefully remove the old batteries, showing a methodical approach to the task, before inserting new ones, ensuring the device is fully functional for upcoming exams. The calculator is placed beside a stack of textbooks and notebooks, highlighting the academic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2121
|
videos/HRA_part2/2121.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 small hamster, characterized by its golden-brown fur and tiny ears, energetically jumps across wooden dock planks by a serene lake, surrounded by lush greenery. The hamster's miniature size contrasts with the vast, natural setting, creating a whimsical scene. Its movements are agile and lively, as it leaps from one dock plank to another, showcasing its playful spirit against the backdrop of a peaceful lakeside environment.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's walking in the video is very unsmooth, and its movements are uncoordinated."
}
] |
seed42_1840
|
videos/HRA_part0/1840.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 janitor, dressed in a yellow safety vest over a gray shirt and black pants, experiences time dilation as he leaps into the air in a high school gymnasium. The scene is captured from four different angles: first, he is seen standing still, looking at the camera. Then, he jumps into the air, the motion slowed down to emphasize the effect of time dilation, his posture mid-leap. In the next frame, he is frozen mid-air, with a basketball hoop and a volleyball net visible in the background. Lastly, he is shown in slow motion again, this time with a look of determination on his face, highlighting the unique experience of time distortion during his jump.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_142
|
videos/HRA_part1/142.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 close-up shot of a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_175
|
videos/HRA_part0/175.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 futuristic space medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated."
}
] |
seed42_2430
|
videos/HRA_part0/2430.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 and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Normal. The deer's head, the waiter's hand, and the pitcher in the hand are generated abnormally; the deer has two mouths."
}
] |
seed46_2293
|
videos/HRA_part2/2293.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 albatross soars through a vivid orange sunset, its expansive wings nearly touching the rippling water below. The bird's white plumage is highlighted by golden light, casting a serene shadow on the sea's surface. Against a dramatic sky, the majestic bird flies gracefully, occasionally gliding over gentle waves. Its wings, outstretched against the horizon, seem to embrace the vastness of the ocean, creating a captivating contrast between the bird's silhouette and the fiery sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2048
|
videos/HRA_part0/2048.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 endearing otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Bad. The otter's movements in the video are not smooth."
}
] |
seed42_3164
|
videos/HRA_part0/3164.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 space station illuminated by neon lights, a lone wolf, distinguished by its silver fur and glowing yellow eyes, walks confidently down a wide corridor. The setting is a grand, high-ceilinged hall with large windows revealing the vastness of space beyond, filled with stars and distant galaxies. The wolf's path leads past a series of closed doors, each marked with the emblem of a different alien species, indicating the location of a significant intergalactic political summit. The wolf's journey is purposeful, moving with determination toward an open door where the summit takes place, set against the backdrop of a stunning cosmic vista.]"
},
{
"from": "gpt",
"value": "Normal. The action of the lone wolf walking is slightly unsmooth."
}
] |
seed44_1173
|
videos/HRA_part1/1173.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 clad in a futuristic, form-fitting, metallic blue bodysuit sprints down the pristine, white corridor of a space-age medical facility, illuminated by soft, ambient lighting. Her athletic build and focused gaze convey urgency and determination. In the next scene, she continues her run, passing by high-tech medical equipment and digital screens displaying complex data. The sleek design of the facility, featuring curved walls and glowing lines, adds a sense of advanced technology. Finally, she reaches a critical area, marked by a large, illuminated circle on the floor, where she stops abruptly, ready to face whatever emergency awaits her.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the woman's limbs in the video is incomplete."
}
] |
seed46_1725
|
videos/HRA_part2/1725.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 pants, serves a dingo seated at a table set amidst dense green thickets. The dingo, wearing a red bandana, looks expectantly at the waiter, who holds a platter of food. Nearby, a swimming pool glistens under the sun, its clear blue water contrasting with the lush vegetation surrounding it. The waiter, with a friendly smile, places the dish before the dingo, who eagerly leans forward, creating a surreal yet charming tableau.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2185
|
videos/HRA_part1/2185.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 an unexpected juxtaposition, a small, fluffy hamster wearing a red life jacket floats in a clear plastic ball filled with water. This unique scene unfolds against the backdrop of an industrial area, complete with factories, smokestacks, and large metal containers. The hamster appears content and relaxed, paddling gently within the ball as it bobs on the water's surface near the edge of a pool. The industrial landscape, featuring tall buildings, cranes, and machinery, provides a striking contrast to the innocent and playful hamster enjoying its unconventional swim.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2722
|
videos/HRA_part2/2722.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 lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the children chasing each other, but the movements are very discontinuous and jerky, and there are noticeable abnormalities in the girl's limbs."
}
] |
seed46_3147
|
videos/HRA_part2/3147.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 surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1381
|
videos/HRA_part1/1381.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 short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Bad. The woman's body and fingers in the video are generated incorrectly."
}
] |
seed44_1134
|
videos/HRA_part1/1134.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 middle-aged janitor, balding with graying hair, meticulously dusts furniture in a large, elegant room filled with antique wooden furnishings, including a desk, a table, and a shelf. He is dressed in a simple gray shirt and brown trousers, moving methodically around the space. He pauses to look at an item on the desk, perhaps a photo or a book, before continuing his work. The room is bathed in warm, golden light from windows not shown, highlighting the dust motes swirling in the air as he works. He finishes by straightening a framed picture on the wall, ensuring everything is perfectly aligned, demonstrating his pride in his work.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not continuous, but the action of wiping the table can be seen."
}
] |
seed42_1672
|
videos/HRA_part0/1672.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."
}
] |
seed46_2755
|
videos/HRA_part2/2755.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 artist, clad in a dark green jacket, beige pants, and brown shoes, walks across a grassy field under a clear blue sky, carrying an easel and a canvas. The focus shifts to reveal a majestic antelope standing in the distance, its silhouette framed by the golden hour sunlight. The artist stops, observing the antelope intently, before setting up the easel and beginning to sketch the graceful creature against the backdrop of a serene landscape. The artist's hands move skillfully over the canvas, capturing the essence of the antelope in motion, with the rolling hills and distant mountains providing a stunning natural setting for this artistic endeavor.]"
},
{
"from": "gpt",
"value": "Bad. No artist wearing a dark green jacket, khaki pants, and brown shoes was generated; there is no movement of the artist's hand on the canvas; the number of antelopes is incorrect."
}
] |
seed42_1701
|
videos/HRA_part0/1701.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, futuristic laboratory, a dedicated scientist wearing a white lab coat crawls beneath an advanced, alien-like machine with glowing blue components, engaged in groundbreaking dark matter research. The complex apparatus looms overhead, resembling a cross between a particle accelerator and a biological organism, with tubes, wires, and screens integrated into its structure. The researcher's focused determination is evident as they navigate the intricate maze of technology, highlighting the challenges and mysteries of exploring the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1204
|
videos/HRA_part2/1204.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 muscular man wearing a beige tank top and khaki cargo shorts jumps powerfully into the air, set against the vivid backdrop of a subtropical desert. The scene captures him mid-leap, showcasing his athletic prowess, with the desert landscape featuring rocky outcroppings and distant mountain ranges bathed in the golden hues of the setting sun. The man's intense focus and the stark beauty of the desert environment combine to create a striking visual narrative, highlighting the contrast between human strength and the vastness of nature.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, the face is twisted, and the arm is deformed."
}
] |
seed42_1112
|
videos/HRA_part0/1112.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, protected national park during autumn, a majestic bull bison with a thick, shaggy brown coat leads a herd across a sunlit meadow, the golden grass swaying gently in the breeze. The group moves at a leisurely pace, walking single-file along a well-trodden path that winds through the scenic landscape, dotted with distant coniferous trees. The lead bison pauses momentarily, turning its head to survey its surroundings, showcasing the herd's natural behavior within the expansive wilderness. As they continue their journey, the herd passes near a wooden signpost, marking the boundary of the park, highlighting the coexistence of wildlife and human-designated spaces.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2473
|
videos/HRA_part2/2473.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 woman dressed in a panther costume, complete with a black leotard, detailed spots, and a lifelike mask, crawls on all fours across a dimly lit stage. The setting is enhanced by a spotlight illuminating her figure, emphasizing the fluidity and grace of her movements, akin to a real panther. The background remains shadowy, drawing attention to her performance as she embodies the essence of the wild animal through her crawling motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2517
|
videos/HRA_part1/2517.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 male worker, wearing a white shirt, beige pants, and a traditional headscarf, is seen wiping the face of a brown camel with a white cloth. The action takes place in a sandy environment, with other camels standing in the background, creating a scene that highlights the care and connection between the worker and the animal. The worker's focused expression and gentle touch convey a sense of respect and familiarity, while the setting sun casts a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video, the item in their hand is distorted, and the camel's face is distorted."
}
] |
seed44_1149
|
videos/HRA_part1/1149.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 vibrant coral reef ecosystem teeming with life, a pair of butterfly fish, one black and one yellow, swim gracefully among the intricate coral formations. The black butterfly fish, adorned with white polka dots and a striking yellow tail, explores a crevice in the coral. Meanwhile, the yellow butterfly fish, featuring intricate black markings, hovers nearby. The scene is illuminated by the warm sunlight filtering through the clear blue water, casting a mesmerizing play of light and shadow on the diverse marine landscape.]"
},
{
"from": "gpt",
"value": "Normal. The fish's eyes were not generated in the video."
}
] |
seed44_1353
|
videos/HRA_part1/1353.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 kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Normal. The kangaroo's hand appears deformed, with two hands suddenly appearing."
}
] |
seed46_2408
|
videos/HRA_part2/2408.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 rugged, seasoned farmer, clad in a futuristic spacesuit with a clear helmet, stands on Mars Base Camp, a sprawling, high-tech habitat amidst the planet's iconic red landscape. The domed settlement, bustling with advanced technology and greenery, contrasts starkly with the desolate Martian terrain. Inside a transparent dome, the farmer enjoys a leisurely swim in a serene pool, surrounded by lush vegetation and state-of-the-art hydroponic farming systems, showcasing the remarkable fusion of agriculture, leisure, and space exploration on the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's walking movements are not continuous."
}
] |
seed44_1837
|
videos/HRA_part1/1837.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 young student, dressed in a casual outfit of a blue jacket and jeans, walks alongside a graceful gazelle through the spacious interior of a futuristic space hotel. The hotel's design features large windows showcasing the vastness of space, with Earth visible in the distance. The student and the gazelle navigate the corridors, passing by otherworldly landscapes displayed on interactive walls. At one point, they pause near a recreational area, where guests can observe cosmic phenomena through a panoramic observatory dome. Throughout their walk, the unique bond between the student and the gazelle is evident, highlighting the extraordinary nature of this extraterrestrial encounter.]"
},
{
"from": "gpt",
"value": "Bad. The interactive wall and the recreational area mentioned in the caption do not appear in the video."
}
] |
seed46_2522
|
videos/HRA_part2/2522.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": "Normal. The jaguar's movements in the video are not smooth."
}
] |
seed42_1304
|
videos/HRA_part0/1304.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 muscular man with short brown hair, wearing a black wetsuit, swims underwater in a clear, blue pool, interacting closely with a live cobra that moves alongside him. The snake, its hood slightly spread, appears calm in the water, its body parallel to the man's outstretched arm. Sunlight filters through the water, casting dappled light on the man's face as he maintains eye contact with the snake, both creatures moving gracefully through the aquatic environment. The scene is set in an outdoor pool, surrounded by lush greenery, emphasizing the natural setting and the unique interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2458
|
videos/HRA_part0/2458.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 ibex, distinguished by its dark brown coat and impressive, backward-curving horns, walks steadily across a rocky mountain landscape, offering a close-up view of its sturdy hooves gripping the stone surface. It moves with purpose, navigating the rugged terrain with ease, its alert eyes scanning the surroundings. The ibex continues its journey, the camera capturing the detail of its textured fur and the dramatic mountain scenery that serves as its habitat, highlighting the animal's resilience and adaptability in its natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1689
|
videos/HRA_part0/1689.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 distinguished lawyer, dressed in a crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Normal. The swimmers in the background appear to have undergone a morphological mutation."
}
] |
seed46_1448
|
videos/HRA_part2/1448.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 room with large windows, a brown bear cub stands on its hind legs, curiously exploring its surroundings at the Space Education Center, filled with educational displays about astronomy. The bear is spotted wiping its nose with a paw, drawing attention to its adorable antics among the exhibits. The scene is set against a backdrop of a large, round, gray planetarium screen, adding a cosmic touch to the unexpected encounter between wildlife and space knowledge.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_251
|
videos/HRA_part0/251.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 engineer wearing a spacesuit decorated with patches and emblems swims effortlessly in zero gravity within a space station habitat. The habitat, illuminated by soft, ambient lighting, features curved walls and large windows offering breathtaking views of the cosmos. A pet lizard, also weightless, floats nearby, its scales reflecting the light in iridescent patterns. The engineer gently propels themselves through the water-filled enclosure, designed to simulate Earth's aquatic environments, while the lizard seems to hover curiously beside them, both adapted to life in the microgravity of the space station.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands, arms, lizard body, head, and feet are distorted in the video."
}
] |
seed42_160
|
videos/HRA_part0/160.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 manta ray glides effortlessly through crystal clear waters, its vast wingspan casting a shadow on the sandy seabed below. The graceful creature is adorned with a constellation of spots and lines, unique to each individual, as it moves with a serene, almost meditative quality. Sunlight filters through the surface, creating a mesmerizing play of light around the manta ray, which occasionally flips upside down to feed on plankton near the water's surface, showcasing its acrobatic abilities in the vibrant marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1701
|
videos/HRA_part2/1701.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 dimly lit, futuristic laboratory, a dedicated scientist wearing a white lab coat crawls beneath an advanced, alien-like machine with glowing blue components, engaged in groundbreaking dark matter research. The complex apparatus looms overhead, resembling a cross between a particle accelerator and a biological organism, with tubes, wires, and screens integrated into its structure. The researcher's focused determination is evident as they navigate the intricate maze of technology, highlighting the challenges and mysteries of exploring the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Normal. The crawling movement of the character in the video is basically normal, but there is some lack of coordination."
}
] |
seed42_1703
|
videos/HRA_part0/1703.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, rustic kitchen, two young children, a boy and a girl, both wearing colorful aprons over their clothes, stand on small wooden stools to reach the sink. The girl, with her hair tied in pigtails, holds a wrench with determination while looking intently at the faucet. The boy, wearing glasses, assists by shining a flashlight on the dripping tap, their teamwork highlighted by the warm, golden glow of the overhead lights. The sink is surrounded by decorative tiles, adding a homely touch to the scene. Tools and parts are neatly arranged on the countertop beside them, emphasizing the organized approach to fixing the leaky faucet.]"
},
{
"from": "gpt",
"value": "Bad. The boy's face and hands, and the girl's hand were generated incorrectly."
}
] |
seed46_3160
|
videos/HRA_part2/3160.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 surreal scene, a well-lit, multi-level highway with heavy traffic serves as the backdrop. Amidst the urban landscape, a unique character takes center stage—a person dressed in a full-body, realistic cat costume, complete with whiskers and a tail. This feline figure energetically performs a captivating dance routine, drawing attention away from the busy city environment. Despite the unusual setting, the dancer's movements are fluid and expressive, adding a touch of whimsy to the concrete jungle. The contrast between the gritty, urban backdrop and the playful, dancing cat costume creates a memorable visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1927
|
videos/HRA_part1/1927.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 creative writer, dressed in a casual green shirt and khaki pants, finds inspiration while leaping energetically onto a large rock in a lush forest setting, as if escaping the ordinary to explore the unknown. Nearby, an awe-inspiring mammoth, seemingly from another time, stands majestically under a canopy of ancient trees, its massive frame and textured skin adding an element of prehistoric wonder to the scene. The juxtaposition of the writer's leap and the mammoth's presence creates a surreal and captivating narrative, blending human creativity with the grandeur of nature's past.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2191
|
videos/HRA_part2/2191.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 captivating scene unfolds, focusing solely on zebrafish within a clear, cylindrical fish tank. The vibrant striped patterns on the zebrafish stand out against the neutral background of the tank, which is devoid of any plants or decorations. The water is crystal clear, allowing every detail of the zebrafish, from their distinctive black and white stripes to their delicate fins, to be visible. The tank is illuminated by overhead lighting, casting a soft glow over the swimming zebrafish, highlighting their movement and the rippling effect they create in the water.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1578
|
videos/HRA_part1/1578.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 creative writer, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1474
|
videos/HRA_part1/1474.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, vibrant forest setting, a mother beaver tenderly caresses her kit with her large, front paw, both sitting cozily within their wooden lodge. The mother, with her brown fur and attentive gaze, gently strokes the smaller beaver, who looks up at her with wide eyes, creating a heartwarming scene of maternal love. The wooden lodge, intricately built from branches and mud, provides a safe and nurturing environment for the family, with green leaves and trees visible in the background, highlighting the beauty of their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. Beaver's hand is twisted, and the face is distorted."
}
] |
seed44_2142
|
videos/HRA_part1/2142.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 man with short brown hair, wearing a gray shirt and glasses, sits in a chair in a living room setting, gently caressing a small, fluffy white cat. The room is filled with natural light from a window behind him, illuminating the intimate interaction. The cat, appearing relaxed and content, lies on its back on the man's lap as he strokes its belly. The scene conveys a sense of warmth and affection between the man and the cat, with the soft focus on their faces capturing the tender moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_165
|
videos/HRA_part2/165.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 space station adorned with lush greenery, a distinguished doctor, wearing a classic white lab coat over a crisp blue shirt, performs a solemn wedding ceremony. The couple, dressed in elegant spacesuits with transparent helmets, exchange loving glances as they gently caress each other's hands, symbolizing their deep connection. Behind them, a panoramic view of the Earth and stars provides a breathtaking backdrop, while the doctor's compassionate demeanor adds a touch of humanity to this extraordinary union in zero gravity.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and there are sudden changes."
}
] |
seed44_2652
|
videos/HRA_part1/2652.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, smiling nurse with a red stethoscope around her neck is seated on a grassy area, holding a small hedgehog in her hands, which looks curious and alert. Behind her, a vibrant, colorful depiction of a quantum leap phenomenon is visible, symbolized by swirling, dynamic patterns of light and color. In the background, a serene swimming pool with clear blue water and lush greenery can be seen, adding a peaceful contrast to the energetic visuals of the quantum leap. The nurse's attire includes a white uniform and name badge, while the hedgehog is depicted in natural detail, its spines clearly visible.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not have any movements."
}
] |
seed42_2153
|
videos/HRA_part0/2153.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 man walks through dense chaparral vegetation, his form occasionally obscured by the thick foliage. He wears a white tank top, beige cargo shorts, and brown hiking boots, his appearance contrasting with the lush greenery. His right hand grasps a walking stick, aiding his navigation through the rugged terrain. As he strides forward, his left arm swings freely, while his right arm, holding the stick, punctuates each step. The vibrant green of the chaparral plants envelops him, emphasizing his journey through this wild landscape.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video holds a hiking stick in his left hand, which does not match the text description."
}
] |
seed46_1371
|
videos/HRA_part2/1371.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 dramatic display, a snake charmer clad in a richly colored red robe and matching turban leans forward, engaging intently with a king cobra emerging from a traditional wicker basket. The snake, adorned with intricate patterns, rises dramatically from the basket, its hood spread wide. The charmer's hands, decorated with silver bracelets, gently caress the serpent's body, emphasizing the bond between human and animal. The scene is set against a vibrant, patterned cloth, adding to the exotic atmosphere, with the charmer's face expressing both respect and control as he interacts with the majestic creature.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's movements are not smooth."
}
] |
seed42_181
|
videos/HRA_part0/181.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 visionary director, wearing a brown jacket, sits on a chair, intently operating a camera, capturing footage of a rhinoceros in a barren desert landscape, with a massive white hole explosion occurring in the distance. The rhinoceros, filmed in extreme close-up, slowly crawls across the sandy terrain, its textured skin and concentrated gaze highlighting its determination. The director, now seen from behind, continues to film the rhinoceros as it traverses the challenging environment, with the white hole explosion's brilliant light illuminating the scene, creating a surreal and captivating contrast between the earthbound creature and the cosmic event.]"
},
{
"from": "gpt",
"value": "Normal. The rhino's movements in the video are unsmooth."
}
] |
seed42_1001
|
videos/HRA_part0/1001.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 smiling firefighter, clad in full gear and a helmet, stands against the backdrop of a fire station. His turnout coat is unzipped, revealing a yellow safety vest, and he holds his helmet in one hand. The fire engine bay is visible behind him, with a red fire truck and a large American flag hanging on the wall. His cheerful demeanor is accentuated by the bright sunlight shining through the open garage door, casting a warm glow over the scene. Despite the serious nature of his profession, his smile conveys a sense of pride, resilience, and community spirit.]"
},
{
"from": "gpt",
"value": "Normal. The rationality is relatively normal."
}
] |
seed46_3035
|
videos/HRA_part2/3035.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 bustling cityscape filled with diverse restaurants, a police officer, clad in a crisp uniform with a badge and cap, stands attentively near a cozy eatery. The scene shifts subtly to focus on the officer gently caressing the head of a loyal K9 partner, who sits attentively beside him, highlighting a tender moment of connection amidst the urban environment. The pair stands out against the backdrop of restaurant signs, patrons enjoying meals, and the vibrant life of the city, capturing a blend of duty and compassion.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements are not smooth."
}
] |
seed44_2173
|
videos/HRA_part1/2173.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 European badger, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Normal. The European badger's face is slightly distorted in the video."
}
] |
seed44_1209
|
videos/HRA_part1/1209.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 teacher, dressed in a lime green shirt and black shorts, runs through a lush, dense forest filled with tall, vibrant trees and thick foliage, the sunlight filtering through the canopy to illuminate the path. The teacher's face is visible, showing determination and focus, with the camera capturing the motion of their legs and feet as they navigate the terrain. The scenery is rich in detail, with various shades of green from the leaves and plants surrounding the runner, and the sounds of nature - birds chirping, leaves rustling - adding to the immersive experience. Throughout the video, the teacher maintains a steady pace, their form suggesting a regular runner enjoying a peaceful jog in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video runs basically normally, with only slightly uncoordinated movements."
}
] |
seed44_1488
|
videos/HRA_part1/1488.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 seasoned firefighter, clad in full gear and a yellow fire-resistant jacket, stands against the backdrop of a blazing inferno, his helmet askew to reveal a focused gaze. Amidst the chaos, he stares intently at the raging fire, his face a mask of determination and resolve. His eyes, shielded by a clear protective visor, never waver from the flames, conveying a sense of duty and bravery in the face of danger. Behind him, the fire rages on, casting an orange glow on his figure, highlighting his steadfast stare and unwavering commitment to extinguishing the blaze.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's movements in the video are basically normal, with slight awkwardness."
}
] |
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 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 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": "Good. Basically correct."
}
] |
seed46_2856
|
videos/HRA_part2/2856.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 cheerful teacher, wearing a yellow blouse and khaki pants, is seen joyfully dancing in a classroom decorated with educational posters. On a nearby desk sits a small, curious gerbil, nibbling on a piece of wood inside its cage. The teacher's energetic movements and warm smile create a vibrant atmosphere, while the gerbil's playful antics add a touch of whimsy to the scene. The camera captures the dynamic interaction between the dancing teacher and the fascinated gerbil, highlighting the unique bond they share within the educational environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2357
|
videos/HRA_part2/2357.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 hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed42_1274
|
videos/HRA_part0/1274.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 fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_258
|
videos/HRA_part0/258.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 female veterinarian, wearing a white lab coat and blue scrubs, gently feeds a small dog from a spoon, her caring nature evident in her warm smile. The clinic room is clean and modern, with stainless steel equipment and a large window providing natural light. Behind her, a poster about pet nutrition hangs on the pale green wall. On a nearby table, various pet food samples are neatly arranged, emphasizing the importance of proper animal care. Throughout the scene, the vet's loving interaction with the dog highlights her dedication to animal welfare.]"
},
{
"from": "gpt",
"value": "Normal. The veterinarian's actions of feeding the dog in the video are basically normal, with slight awkwardness."
}
] |
seed46_1687
|
videos/HRA_part2/1687.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 close-up view captures a mole crab, also known as a sand flea, burrowing in the wet sand of a tropical beach. Its sandy brown color perfectly camouflages it against the shoreline, and its shovel-like front legs dig rapidly into the granular substrate. The creature's round body and small size, about an inch long, make it appear as if it's almost melting into the sand, while its eyes, positioned on stalks, scan the environment for predators or prey. The video highlights the mole crab's unique adaptation for life in the intertidal zone, showcasing its survival tactics in the dynamic coastal ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab in the video has a twisted body and legs."
}
] |
seed46_2385
|
videos/HRA_part2/2385.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 dressed in a yellow shirt, green vest, and brown shorts leaps into the air with his arms extended above his head, against a backdrop of dense subtropical forest. The lush green foliage, including palm fronds and ferns, provides a vibrant setting. In another frame, he jumps again, this time with his arms wide open, wearing a white cap, dark sunglasses, and a smile, against a similar background of rich, verdant trees. Throughout the sequence, the man's joyful expressions and dynamic poses capture the essence of his energetic exploration within the vibrant subtropical woodland environment.]"
},
{
"from": "gpt",
"value": "Bad. The man's walking and jumping in the video are very unsmooth, and his movements are uncoordinated."
}
] |
seed44_1151
|
videos/HRA_part1/1151.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, donning a black beret and glasses, sits at a cluttered desk in a dimly lit room, affectionately caressing a small bat perched on her finger. The bat, appearing relaxed and comfortable, is nestled against her hand, which is adorned with silver rings. The scene is set against a backdrop of bookshelves filled with various books, adding to the intellectual and mysterious atmosphere. The writer's other hand rests on a vintage typewriter, hinting at her profession, while the bat's presence introduces an element of the unusual into the intimate scene.]"
},
{
"from": "gpt",
"value": "Bad. The bat and the character's hand generation in the video is problematic, and the vintage typewriter was not generated."
}
] |
seed46_3063
|
videos/HRA_part2/3063.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 police officer, clad in a navy uniform with a badge and utility belt, walks alongside a cheetah on a leash in an urban park setting. The officer, wearing sunglasses and a cap, maintains a calm demeanor as they stroll together. The cheetah, fitted with a specialized harness, looks up attentively, its spots clearly visible against the green foliage of the park. The pair meanders past park benches and trees, creating an unusual yet harmonious scene of law enforcement and wildlife coexisting in a city environment.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the police officer and the cheetah walking, but the movements are not smooth."
}
] |
seed44_2723
|
videos/HRA_part1/2723.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 compassionate nurse, wearing a blue medical uniform, pauses in a hospital room to appreciate a vibrant painting hanging on the wall. The artwork depicts a lush forest landscape, filled with shades of green, brown, and blue, evoking a sense of peace and tranquility. Sunlight filters through the painted trees, casting a warm glow on the nurse's face as she stands beside a patient's bed, momentarily lost in the serene scene before her. The contrast between the sterile hospital environment and the natural beauty of the painting highlights the nurse's ability to find moments of calm amidst the demands of her profession.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2329
|
videos/HRA_part1/2329.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 construction worker, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's jumping motion in the video is discontinuous, and there are abrupt changes in the limbs."
}
] |
seed42_1312
|
videos/HRA_part0/1312.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 magnificent white swan floats regally on a tranquil lake, its reflection shimmering in the water. The swan, with its long, curved neck and proud demeanor, glides effortlessly, surrounded by lush green vegetation on the banks. Its wings, partially extended, display the exquisite feather patterns, while its webbed feet gently propel it forward. The serene atmosphere is enhanced by the soft, natural lighting that illuminates the scene, capturing the swan's every graceful movement on the mirror-like surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1027
|
videos/HRA_part0/1027.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 writer, clad in a red jacket, blue jeans, and black running shoes, races through the bustling city streets at night, passing by a diverse array of shops and restaurants. The urban landscape is illuminated by the glow of neon signs and streetlights, casting dynamic shadows as the runner weaves through the crowd. The scene captures the energy and vibrancy of city life, with the writer's determination and focus highlighted by the motion blur of the passing scenery. The narrative unfolds as the runner passes landmarks like a movie theater, a busy crosswalk, and a street food vendor, all contributing to the vivid tapestry of the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's legs are twisted in the video."
}
] |
seed46_180
|
videos/HRA_part2/180.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 dry forest, a director wearing a black jacket, blue jeans, and a wide-brimmed hat is seen intently choreographing a dance sequence. The dancers, dressed in flowing white garments, perform intricate steps amidst the tall, gnarled trees and dappled sunlight. The director gestures dramatically, guiding the dancers through their routine, while the vibrant green foliage and unique flora of the subtropical dry forest provide a stunning natural backdrop. Throughout the scene, the focus remains on the passionate direction and the captivating dance performance set within the enchanting forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.