video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2888
|
videos/HRA_part0/2888.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 theater, the spotlight reveals two young children, a boy and a girl, both dressed in casual attire, sitting on a red velvet couch. The boy, wearing a blue T-shirt and khaki shorts, looks at the girl with a smile, his hand gently caressing her arm. The girl, dressed in a yellow sundress, returns his affectionate gesture with a warm look and a tender touch to his cheek, all against the backdrop of a classic theater setting with plush red curtains and ornate decorations. The scene captures a moment of innocent connection between the two children, emphasizing the tenderness of their interaction within the grandeur of the theater environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2699
|
videos/HRA_part0/2699.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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The egret's walking in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1083
|
videos/HRA_part1/1083.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 lush, verdant jungle setting, a group of intrepid explorers clad in khaki safari gear navigate a narrow, foliage-lined path, their expressions a mix of determination and awe. They pause momentarily, observing a majestic silverback gorilla ambling nearby, its powerful form moving gracefully through the underbrush. The gorilla, seemingly undisturbed by the presence of humans, continues its journey, highlighting the peaceful coexistence between wildlife and respectful visitors in this pristine natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2980
|
videos/HRA_part2/2980.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 man, dressed in a brown jacket, beige pants, and brown boots, stands on a dirt floor, meticulously wiping a wooden table with a cloth. The scene takes place in a large, open arena, filled with wooden tables and chairs, reminiscent of a medieval feast setting. Sunlight filters through the high windows, casting a warm glow over the space. The man's focused gaze and the repetitive motion of his hand convey a sense of purpose and care in his task, set against the vastness of the arena.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed44_2546
|
videos/HRA_part1/2546.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 farmer with short, dark hair and a neatly trimmed beard stands on a wooden chair, set atop a checkered floor, inside a rustic barn illuminated by soft, warm lighting. Dressed in a plaid shirt, blue jeans, and a brown vest, he reaches up to change a light bulb, his face reflecting concentration. The barn's wooden structure, adorned with tools and equipment, provides a backdrop for this everyday task, highlighting the farmer's practical skills and the cozy, well-lit interior of the barn.]"
},
{
"from": "gpt",
"value": "Normal. Failed to generate a wooden chair."
}
] |
seed44_269
|
videos/HRA_part1/269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, misty forest setting, a majestic bull moose with a full rack of antlers tenderly nuzzles a smaller female moose, both enveloped in the early morning light filtering through the trees. Their interaction is gentle and intimate, showcasing the softer side of these typically solitary creatures. The male's large, furry body and impressive antlers contrast with the delicate nature of their caress, highlighting the bond between them. The scene is set against a backdrop of lush vegetation and tall trees, creating a peaceful and private moment in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The antlers of the red moose in the video are generated unreasonably, the eyes are generated strangely, the facial features of the fawn are not generated, and the limbs are missing."
}
] |
seed42_2501
|
videos/HRA_part0/2501.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 cave, a police officer, wearing a uniform with a badge and a utility belt equipped with various tools, including a flashlight, gently caresses the rough stone wall, seemingly searching for hidden clues or evidence. The cave's textured walls, illuminated by the officer's flashlight, provide a dramatic backdrop for this intense moment of investigation. The officer's focused gaze and careful touch convey a sense of determination and meticulousness in uncovering secrets within the cave's depths.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3134
|
videos/HRA_part2/3134.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 professional lawyer, dressed in a casual yet stylish ensemble of a gray turtleneck sweater and black pants, stands in a modern kitchen with sleek, stainless steel appliances. The individual focuses intently on preparing a gourmet meal, chopping ingredients on a wooden cutting board placed atop a granite countertop. The kitchen is illuminated by recessed ceiling lights, casting a warm glow over the scene. Behind the chef, a large window allows a view of a city skyline at twilight, adding a touch of urban sophistication to the domestic setting. The lawyer's movements are confident and practiced, indicating a comfort in both the courtroom and the culinary arts.]"
},
{
"from": "gpt",
"value": "Normal. The man's hands undergo a deformity mutation while chopping vegetables."
}
] |
seed44_2664
|
videos/HRA_part1/2664.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 doctor, wearing a brown jacket over a white shirt and khaki pants, walks through a temperate deciduous forest during autumn. The trees are predominantly bare, with scattered leaves covering the ground. The forest floor is carpeted with a thick layer of dry, brown leaves, creating a crunching sound underfoot. The doctor occasionally stops to observe his surroundings, showcasing his appreciation for nature. Throughout the scene, the forest remains dense and the trees tall, with occasional glimpses of sunlight filtering through the canopy, highlighting the serenity of the environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_2392
|
videos/HRA_part0/2392.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 close-up of a vibrant green lizard, its textured skin detailed, as it sits on a wooden branch in a lush swamp environment. The scene is set in a dense, swampy forest, with the lizard performing a wiping motion across its eye, a behavior often observed in the wild. The background is filled with the rich greens of swamp vegetation, creating a vivid contrast against the lizard's striking appearance. Throughout the video, the focus remains on the lizard's actions, particularly the wiping gesture, which adds an element of intrigue and natural behavior to the footage.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2691
|
videos/HRA_part1/2691.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2252
|
videos/HRA_part2/2252.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 green sweater and brown trousers, kneels on a lush, grassy field as they observe a graceful gazelle. The writer, with a notebook in hand, carefully documents the gazelle's movements from a crawling position, capturing the serene atmosphere under a clear blue sky. The scene highlights the writer's dedication to their craft, as they immerse themselves in nature to gather inspiration, while the gazelle, unaware of the observer, continues its elegant grazing nearby.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1611
|
videos/HRA_part1/1611.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 octopus, showcasing its remarkable camouflage abilities, rests on a sandy seabed, its body appearing as a collection of scattered stones and sand patches. It then changes color and texture, mimicking a cluster of sponges and corals, demonstrating its incredible mimicry skills. Next, it displays a pattern resembling seaweed and plant life, swaying gently as if caught in an underwater current. Finally, the octopus morphs into an imitation of a rocky outcrop, complete with algae and barnacles, further highlighting its extraordinary ability to blend into various marine environments.]"
},
{
"from": "gpt",
"value": "Normal. The seaweed on the octopus in the video is excessive."
}
] |
seed44_3066
|
videos/HRA_part1/3066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vibrant scene, a group of people wearing colorful swimsuits swim in a large, clear pool, with a majestic giraffe standing nearby, observing the swimmers with curiosity. Overhead, a futuristic Photon sail floats gracefully in the sky, reflecting sunlight and casting dynamic shadows onto the water below. The people interact with the giraffe gently, feeding it leaves, while the sail continues its serene journey across the sky, creating a harmonious blend of nature and advanced technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1193
|
videos/HRA_part1/1193.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 cheerful, young female teacher dances joyfully on a wide, sandy beach, her bare feet sinking into the warm sand as she moves. Dressed in a vibrant, floral-print sundress and a denim jacket, she twirls with her arms extended, embracing the freedom and beauty of the seaside. The sun casts a golden glow on the beach, highlighting her graceful silhouette as she dances with abandon, surrounded by the vast, serene ocean and clear, blue skies. Her carefree spirit and the stunning beach scenery create a captivating, uplifting scene.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video dances very unsmoothly, with uncoordinated movements."
}
] |
seed42_2446
|
videos/HRA_part0/2446.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 hazy, ethereal atmosphere of Neptune, a space-suited firefighter, equipped with a specialized breathing apparatus and protective gear, is seen wiping the visor of his helmet. A neon bat, adapted to the planet's unique environment, hangs upside-down from a rocky outcropping nearby, its vibrant wings contrasting against the dimly lit, gaseous landscape. The firefighter's actions are deliberate and methodical, emphasizing the importance of maintaining clear visibility in the challenging conditions of Neptune's alien skies.]"
},
{
"from": "gpt",
"value": "Bad. The bat generation in the video is abnormal."
}
] |
seed46_1473
|
videos/HRA_part2/1473.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 European bee-eater perches on a branch, its vibrant green feathers contrasting against a clear blue sky, before taking flight against a backdrop of lush greenery and distant mountains. It swoops down gracefully, its long, slender beak aimed at capturing prey. The bird then returns to the branch, where it proudly displays its catch, a honeybee, before consuming it. Throughout the scene, the bee-eater's striking plumage, featuring shades of green, blue, and brown, catches the eye against the serene landscape.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and there is a sudden change. The bee that the hawk was carrying suddenly disappears."
}
] |
seed46_2970
|
videos/HRA_part2/2970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a young female cashier, wearing a red apron over her gray sweater and black jeans, stands at a register, looking surprised. Behind her, a full-sized moose runs across the store, its antlers adorned with Christmas lights, adding a surreal touch to the supermarket setting. The moose dashes between the aisles filled with groceries, creating a chaotic yet amusing atmosphere. The cashier watches the unexpected visitor with a mix of shock and amusement, as customers look on in disbelief, capturing the bizarre event on their smartphones. The moose's presence disrupts the mundane routine of the store, turning it into an unforgettable experience for everyone present.]"
},
{
"from": "gpt",
"value": "Bad. The moose's body is twisted, its head is twisted, its feet are twisted, its legs are twisted, and the female cashier's face is distorted."
}
] |
seed42_142
|
videos/HRA_part0/142.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."
}
] |
seed46_1804
|
videos/HRA_part2/1804.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 man, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, head, arms, and legs."
}
] |
seed44_2442
|
videos/HRA_part1/2442.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic tiger, drenched in sunlight, strides into a serene pond, its striped coat shimmering against the clear water. Gracefully, it begins to swim, powerful paws propelling it forward, with droplets scattering from its body. The water's surface reflects the lush greenery surrounding the pond, creating a tranquil atmosphere as the tiger continues to paddle through the calm waters, highlighting its unexpected aquatic prowess.]"
},
{
"from": "gpt",
"value": "Normal. The tiger's swimming movements in the video are not smooth and coordinated."
}
] |
seed42_3003
|
videos/HRA_part0/3003.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 cozy, softly lit room, two young children sit on a patterned carpet, engrossed in play, wearing casual clothing suitable for a relaxed day indoors. One child, dressed in a yellow shirt and blue shorts, leans forward with curiosity. Beside them, a ferret, identifiable by its distinct brown and white fur, explores the space, crawling across the floor with agile movements. The scene captures a moment of innocent delight, as the children and the ferret interact in a safe and supervised environment, the warm colors and textures adding to the sense of comfort and security.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1117
|
videos/HRA_part1/1117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's ears disappear when it moves in the middle of the video, and its paws suddenly disappear or reappear."
}
] |
seed44_2856
|
videos/HRA_part1/2856.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. Basically no problem."
}
] |
seed46_2987
|
videos/HRA_part2/2987.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 cheerful nurse, wearing a vibrant floral-print dress over her swimsuit, stands before a majestic waterfall cascading into a serene pool. She joyfully leaps into the water, her dress fluttering in the breeze, revealing her red swimwear beneath. Emerging from the pool, she playfully splashes water, her laughter echoing through the lush, green surroundings. As she exits the frame, a panoramic view of the waterfall and its misty spray enveloping the tranquil pool takes center stage, offering a peaceful contrast to the nurse's lively energy.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's jump into the water in the video is not smooth."
}
] |
seed44_294
|
videos/HRA_part1/294.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 passionate teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher can be clearly seen dancing in the video, but the movements are very discontinuous, and there are sudden changes in the limbs."
}
] |
seed42_1479
|
videos/HRA_part0/1479.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 prehistoric mammoth, covered in shaggy, dark brown fur, stands against a pale, sandy background. It uses its trunk to wipe mud from its body, creating a cloud of dust that catches the sunlight. The creature's large, curved tusks and drooping ears are prominent as it continues to clean itself, highlighting its ancient majesty in a moment captured with high-definition clarity.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are basically normal, with slight inconsistency."
}
] |
seed46_2946
|
videos/HRA_part2/2946.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 stunning close-up of a halibut fish, flat and wide, with a mottled brown and white skin pattern, is showcased against a dark background. The fish has a large, open mouth with small teeth visible, and its eyes are set on the left side of its head, gazing intently. The texture of the halibut's skin is detailed, showing rough spots and a rugged surface, while the background remains uniformly dark, highlighting the unique features of this deep-sea dweller.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2626
|
videos/HRA_part0/2626.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 captivating underwater scene, a cluster of jellyfish, predominantly moon jellyfish, gracefully floats in a harmonious formation. Their translucent bell-shaped bodies, illuminated by a soft blue light, reveal intricate patterns and textures. Surrounding them are various marine creatures, including small fish and other jellyfish species, adding to the vibrant ecosystem. The jellyfish pulsate rhythmically, propelling themselves through the water, while their trailing tentacles gently undulate, creating a mesmerizing visual display in this serene aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_188
|
videos/HRA_part2/188.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, a species of wild mountain goat, is shown crawling on all fours across a rocky terrain. The scene is set in a mountainous region, with steep cliffs and rugged landscape providing a challenging environment for the animal. The ibex is depicted in a vulnerable position, moving slowly and deliberately as it navigates the uneven surface. Its body is in a low, crawling stance, highlighting its agility and strength in adapting to harsh conditions. The camera captures this intimate moment in high definition, focusing solely on the ibex as it crawls, emphasizing the creature's resilience and survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2820
|
videos/HRA_part2/2820.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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's face in the video is generated with slight blurriness."
}
] |
seed42_1135
|
videos/HRA_part0/1135.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, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not fluid, and the movements are uncoordinated."
}
] |
seed42_2559
|
videos/HRA_part0/2559.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 dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed42_1513
|
videos/HRA_part0/1513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_214
|
videos/HRA_part2/214.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 college student, casually dressed in a white T-shirt and blue jeans, diligently paints a room with bright yellow walls, focusing on a corner where two walls meet. The room is filled with natural light from a nearby window, illuminating the student's task. They wear protective goggles and a face mask, ensuring safety while working. The student is surrounded by painting supplies, including a ladder, paint cans, and brushes, indicating a thorough preparation for the project. As the camera pans out, we see the student's friends in similar attire, contributing to the painting effort, fostering a sense of camaraderie and teamwork in transforming the space.]"
},
{
"from": "gpt",
"value": "Bad. The student's actions of painting the wall in the video are not continuous, with abrupt changes."
}
] |
seed44_2155
|
videos/HRA_part1/2155.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 bald eagle soars gracefully through the crisp, clear sky, its powerful wings spread wide against a backdrop of fluffy white clouds and a vibrant blue horizon. The eagle's piercing golden eyes and distinctive white-feathered head stand out prominently. It effortlessly glides over a vast, pristine landscape, featuring lush green forests and shimmering lakes, with the distant silhouette of snow-capped mountains providing a breathtaking contrast. The eagle's strong, brown body and large, feathered tail complete the image of this awe-inspiring bird in flight.]"
},
{
"from": "gpt",
"value": "Bad. The bald eagle's wing-flapping motion in the video is discontinuous and lacks coordination."
}
] |
seed42_1604
|
videos/HRA_part0/1604.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 T-shirt and dark green shorts, carefully loads dishes into a stainless steel dishwasher in a modern kitchen. The room is brightly lit, casting clear shadows and revealing the intricate details of the kitchen, including the tile backsplash and granite countertops. The student, with short brown hair and glasses, methodically organizes the plates, bowls, and silverware, demonstrating responsibility and attention to detail. Throughout the process, the student maintains a focused demeanor, occasionally pausing to ensure each item is securely placed, all within the well-lit, contemporary kitchen environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2583
|
videos/HRA_part0/2583.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 police officer, clad in a full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_140
|
videos/HRA_part2/140.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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_3153
|
videos/HRA_part0/3153.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, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Normal. The painter's hand is slightly deformed."
}
] |
seed44_2989
|
videos/HRA_part1/2989.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 kitchen illuminated by neon lights, a chef wearing a sleek, silver uniform and gravity-defying boots stands aboard an anti-gravity vehicle. The vehicle, resembling a levitating platform with intricate, glowing circuitry, hovers above a metallic countertop cluttered with advanced cooking gadgets. The chef, with a focused gaze, wipes a stainless steel utensil with a microfiber cloth, preparing for culinary innovation amidst the backdrop of a high-tech, floating workstation.]"
},
{
"from": "gpt",
"value": "Normal. The chef's face, hands, and arms are distorted in the video."
}
] |
seed42_1042
|
videos/HRA_part0/1042.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 mature woman with graying hair tied in a ponytail engages in a fall activity, raking leaves in her spacious backyard. Dressed in a blue shirt, denim jacket, and brown gloves, she meticulously gathers the autumn foliage. The scene is set in late afternoon, as indicated by the soft, golden light filtering through the trees. She pauses to look up, her expression one of determination mixed with a sense of accomplishment, surrounded by piles of leaves and a red wheelbarrow nearby, emblematic of the season's chores and the beauty of nature's transition.]"
},
{
"from": "gpt",
"value": "Bad. The fingers of the hand are not generated, and the tool held in the hand is bent and deformed. The face is also deformed."
}
] |
seed42_1256
|
videos/HRA_part0/1256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vivid scene, a writer, presumably the main character, runs along a sandy path at a luxurious resort, set against a backdrop of lush greenery and palm trees. Dressed in a gray tank top, black shorts, and black running shoes, he wears a determined expression as he focuses ahead. Accompanying him is a black jackal, resembling a wild dog, which runs alongside him, adding a sense of companionship and adventure to the narrative. The resort's opulent buildings and facilities are visible in the background, highlighting the contrast between nature and luxury.]"
},
{
"from": "gpt",
"value": "Bad. The running actions of the writer and the jackal in the video are not smooth and lack coordination."
}
] |
seed44_2477
|
videos/HRA_part1/2477.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 engineer wearing a high-visibility jacket walks along the edge of a bustling harbor, the sunlight glinting off the water and reflecting onto his safety glasses. He carries a clipboard in one hand, attentively observing the large ships and cranes at work. The harbor is alive with activity, from the loading and unloading of cargo to the movement of tugboats guiding massive vessels. In the distance, the silhouette of a city skyline adds a touch of urbanity to the industrial scene. The engineer stops occasionally to jot down notes, his expertise evident in his confident demeanor and the precision with which he performs his duties.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2674
|
videos/HRA_part1/2674.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 college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, and his movements are uncoordinated."
}
] |
seed44_2243
|
videos/HRA_part1/2243.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 charismatic musician, clad in a vibrant yellow raincoat and matching hat, stands under a powerful waterfall in a lush, green forest, playing a harmonica with intense focus. The water cascades over mossy rocks, creating a natural stage for the performer. Suddenly, the musician leaps into the air, harmonica still in mouth, capturing a moment of pure joy and freedom amidst the thundering water and verdant surroundings. The scene is framed by towering trees and ferns, emphasizing the connection between music, nature, and human spirit.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1367
|
videos/HRA_part1/1367.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 film director, wearing a dark jacket, jeans, and a baseball cap, runs energetically across a futuristic space movie set, filled with intricate machinery and high-tech equipment. The set features large, circular structures and metallic surfaces, giving it a distinctly sci-fi aesthetic. The director's movement conveys a sense of urgency and purpose, as he navigates through the complex environment, surrounded by the vast, industrial-like backdrop of the space station set.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is flying, with dislocation and deformity. The legs also show deformity."
}
] |
seed42_2833
|
videos/HRA_part0/2833.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 farmer, clad in a red flannel shirt and denim overalls, is seen exerting effort as he pulls on a thick rope. The scene is set on a vast, green farm, with lush fields stretching into the horizon. The farmer's weathered hands grip the rope tightly, his face contorted in determination, highlighting the physical demands of his labor. Behind him, a wooden barn with a rusty roof provides a rustic backdrop, while the clear blue sky above adds a sense of serenity to the hardworking atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1906
|
videos/HRA_part1/1906.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 skilled musician, garbed in a vibrant red jacket, plays a traditional wooden flute, his eyes closed in concentration, set against a backdrop of rolling hills and lush greenery. In the foreground, an ibex, distinguished by its curved horns, leaps gracefully over a small obstacle, embodying freedom and agility. The harmonious blend of the musician's melodic tunes and the ibex's acrobatic leap creates a captivating scene, where nature and artistry coalesce beautifully under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2378
|
videos/HRA_part1/2378.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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2258
|
videos/HRA_part1/2258.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 man, reminiscent of Jason Statham, with short, dark hair and a chiseled jawline, wearing a torn gray tank top, tattered khaki pants, and combat boots, stealthily walks through a dimly lit space station corridor. The setting is a gritty, futuristic prison, with cold steel walls, flickering neon lights, and a tense atmosphere. The man moves with purpose and determination, his eyes scanning the surroundings for any sign of danger. In one shot, he pauses, listening intently, before continuing his escape mission. Throughout the sequence, the tension builds as he navigates the confined spaces of the prison, evoking a sense of suspense and urgency.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1883
|
videos/HRA_part1/1883.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 musician, donning a dark jacket and distressed jeans, stealthily walks through the dimly lit corridors of a futuristic space prison. His intense gaze is directed ahead, revealing his determination. The harsh, cold lighting accentuates the high-tech, metallic surfaces of the prison environment. As he moves, the camera captures the tension in his body language, hinting at the imminent danger. Despite the oppressive surroundings, the musician's confident stride and unwavering focus suggest a plan in motion, ready to execute his daring escape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1894
|
videos/HRA_part2/1894.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 lawyer, dressed in a navy suit, white shirt, and striped tie, races through a lush green forest, holding a koala in one arm. The koala, clinging tightly, wears a tiny barrister's wig and round spectacles, adding a whimsical touch to the scene. They run past tall trees, ferns, and flowers, with the lawyer's facial expressions alternating between determination and a smile, highlighting the unusual yet playful nature of the chase. The vibrant forest setting, complete with sunlight filtering through the leaves, enhances the dynamic and surreal atmosphere of the scenario.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2797
|
videos/HRA_part0/2797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged explorer, traverses a dense tropical dry forest, wiping beads of sweat from his brow. Surrounded by towering trees with gnarled roots and sparse foliage, he navigates the arid landscape, dressed in khaki cargo pants, a beige tank top, and a wide-brimmed hat. The scene is illuminated by the golden glow of late afternoon sunlight filtering through the canopy, casting dappled shadows on the ground. The explorer pauses, wiping away perspiration with a cloth, revealing a map in his hands, hinting at his quest for hidden treasures within the unforgiving yet enchanting wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The explorer's movements in the video are not smooth."
}
] |
seed46_2448
|
videos/HRA_part2/2448.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 chimpanzee, characterized by its dark fur and physical strength, leaps powerfully from a low branch in a lush, green forest. The chimp, wearing a radio collar for tracking purposes, is seen mid-jump, demonstrating its agility and vitality. Its movement is captured in high definition, highlighting the details of its fur and the determination in its eyes. The chimpanzee propels itself forward, leaving the branch behind, showcasing its natural habitat and behaviors in a captivating, close-range shot.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the chimpanzee wearing a radio collar as mentioned in the caption."
}
] |
seed44_1153
|
videos/HRA_part1/1153.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 male worker, wearing a brown shirt and green shorts, attentively wipes an Asian elephant's face using a small cloth. The elephant, with its trunk slightly raised, stands calmly next to a wooden structure within a spacious enclosure, possibly at a wildlife sanctuary. The man continues to clean the animal's eye area, showing care and familiarity, while the elephant remains still, indicating a trusting relationship between the two. Throughout, the worker focuses on his task, gently tending to the creature's needs in a peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1919
|
videos/HRA_part0/1919.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin breaches the shimmering ocean surface, its streamlined body glistening under the golden sunlight. The marine creature, adorned with striking blue and silver hues, soars through the air with acrobatic grace, its elongated upper jaw, or rostrum, pointing towards the sky. As it re-enters the water, a splash of crystal-clear droplets disperses around it, creating a mesmerizing display of power and agility in the vast aquatic realm.]"
},
{
"from": "gpt",
"value": "Normal. There is an issue with the fin generation."
}
] |
seed44_3102
|
videos/HRA_part1/3102.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 fantastical prehistoric scene, a massive woolly mammoth leaps over a frozen log in a snow-covered forest during the Ice Age, with tall pine trees framing the action. The mammoth, complete with shaggy brown fur and impressive tusks, is captured mid-air, its large body defying expectations as it clears the obstacle with surprising agility. The icy landscape, dotted with ancient conifers, adds to the dramatic effect of this unlikely jump, highlighting the creature's strength and adaptability in its harsh environment.]"
},
{
"from": "gpt",
"value": "Bad. The mammoth's teeth generation in the video has problems, there is a missing part in the leg generation, and the claws and nose are deformed."
}
] |
seed44_125
|
videos/HRA_part1/125.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 woman wearing a vibrant yellow apron over a casual outfit of a gray t-shirt and black leggings, her brown hair tied back in a ponytail, is seen cooking in a modern kitchen. She expertly chops vegetables on a wooden cutting board using a sharp knife, the overhead lights reflecting off the stainless-steel appliances behind her. Her hands, adorned with rings, move with practiced ease as she seasons the ingredients in a large skillet on a gas stove, steam gently rising from the pan. Throughout, she maintains a warm smile, occasionally glancing up from her task, creating an inviting atmosphere in the well-lit kitchen space.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video is not wearing black leggings."
}
] |
seed46_2809
|
videos/HRA_part2/2809.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 dimly lit, elegant restaurant, a cunning weasel, dressed in a crisp white waiter's outfit with a black bow tie, gracefully crawls across a wooden floor, passing beneath a table draped with a pristine white cloth. The weasel's sleek body and sharp features are accentuated by the warm glow of candlelight, casting dramatic shadows as it moves stealthily, weaving between the legs of ornate chairs. Its eyes gleam with mischief, hinting at some secretive mission unfolding among the unsuspecting diners.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's body is twisted, its head is twisted, and its claws are twisted."
}
] |
seed42_2157
|
videos/HRA_part0/2157.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 small vole, brown with white underparts, scurries along a paved path between two large apartment complexes, their exteriors a mix of brick and siding, under a partly cloudy sky. The rodent navigates the concrete walkway, dotted with cracks and weeds, passing by the base of the buildings where potted plants and bicycles are stored. It continues its journey undisturbed, weaving between the structures that tower above it, set against the backdrop of a suburban neighborhood with cars parked along the street and other apartment buildings visible in the distance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1051
|
videos/HRA_part0/1051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male grouse, distinguished by its dark brown feathers and a distinctive red wattle above the eyes, stands prominently on a fallen tree in the middle of a dense, green forest. The bird's posture is alert, its head held high, indicating readiness for flight or fight. The forest surroundings are lush and verdant, with sunlight filtering through the canopy, highlighting the grouse's textured plumage. The setting is peaceful, with no visible disturbances, allowing the grouse to maintain its dominant position on the log, a symbol of its territorial claim within the woodland habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_246
|
videos/HRA_part0/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2959
|
videos/HRA_part1/2959.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 director, distinguished with salt-and-pepper hair and a trimmed beard, stands in a dimly lit, cluttered bathroom. Dressed casually in a gray t-shirt, dark jeans, and a black jacket, he focuses intently on unclogging a blocked sink drain. His right hand grips a metal tool, while his left hand steadies the sink's rim. The scene captures his determination, with the bathroom's sparse details - a white toilet, a beige wall, and a small window - adding context to his solitary task. The director's serious demeanor and the bathroom's functional design emphasize the mundane yet necessary act of home maintenance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1875
|
videos/HRA_part0/1875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a white shirt and denim overalls, stands on the edge of a serene pond, watching attentively as a rabbit swims gracefully through the clear water. The rabbit, defying expectations, moves with surprising agility, its brown fur glistening beneath the golden afternoon sunlight. The farmer, hat in hand, looks on with a mix of surprise and delight, the rolling green fields and distant barn providing a quintessential rural backdrop to this unexpected scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_265
|
videos/HRA_part0/265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit chaparral landscape, a seasoned farmer wearing a wide-brimmed straw hat, denim overalls, and a plaid shirt is seen joyfully dancing. In the background, a jackal curiously observes from a distance, standing near a weathered wooden fence. The farmer, embodying the spirit of the land, performs lively dance moves, celebrating the beauty of nature around him, with the jackal occasionally mirroring his movements in a playful manner. The chaparral vegetation, characterized by shrubs and small trees, forms a picturesque setting for this unexpected dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed44_1037
|
videos/HRA_part1/1037.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, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_200
|
videos/HRA_part0/200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 single camel, distinguished by its brown fur and a patterned red, yellow, and green saddle, stands against a desert landscape under a clear blue sky. It begins to move rhythmically, swaying to an unseen beat, its large eyes gazing into the distance. Moments later, it raises its head proudly, its mouth open in a gesture that suggests a joyful call or song. Then, the camel continues its dance, gracefully moving its legs in time with the music, its body language conveying a sense of happiness and freedom in the vast, sandy expanse.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1474
|
videos/HRA_part2/1474.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 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, 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. The mother beaver's actions of petting the baby in the video are basically normal, with only slight awkwardness."
}
] |
seed44_2275
|
videos/HRA_part1/2275.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 doctor, identifiable by his blue scrubs and stethoscope, walks steadily in zero gravity, orbiting the Earth inside a space station illuminated by the planet's stunning blue and green hues. He maneuvers through the microgravity environment with ease, pushing off surfaces to navigate his path. At one point, he floats near a window displaying the Earth's horizon, backlit by the sun, offering a breathtaking view of our planet from orbit. Throughout the scene, the doctor's calm demeanor and the serene backdrop of Earth's curvature underscore the unique experience of walking in space.]"
},
{
"from": "gpt",
"value": "Bad. The person's arms, hands, feet, legs, and face are distorted in the video."
}
] |
seed44_3071
|
videos/HRA_part1/3071.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 astronaut, clad in a spacesuit adorned with patches and equipped with a jetpack, orbits the Earth while holding a moose, its antlers visible. Below, on a pristine planet, a worker in a blue uniform tends to a pool, where a moose swims leisurely, its large frame gliding through the crystal-clear water. The worker, wearing a blue cap, looks up at the space-suited figure and the orbiting moose, a sense of wonder in their eyes. This juxtaposition of scenes captures the surreal and unexpected elements of life in space and on Earth.]"
},
{
"from": "gpt",
"value": "Bad. No jetpack was generated, and the worker is wearing a blue uniform."
}
] |
seed44_199
|
videos/HRA_part1/199.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, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The park bench mentioned in the caption does not appear in the video."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate 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 nurse's hand shows a deformed mutation, and the spoon in her hand also becomes bent."
}
] |
seed46_1720
|
videos/HRA_part2/1720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large grouper fish, displaying a mottled brown and white skin pattern, swims serenely in clear blue waters, its wide mouth and curious eyes prominent. It passes by a vibrant coral reef, home to smaller, colorful fish darting in and out of the crevices. The sunlight filters through the water, casting dappled light on the sandy ocean floor and highlighting the intricate details of the grouper's body and its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3206
|
videos/HRA_part2/3206.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 cave, a small brown bat crawls along the rocky surface, using its wings as makeshift limbs for terrestrial navigation. The bat's eyes are closed, relying on echolocation to sense its surroundings, while its furry body brushes against the damp stone. Nearby, water droplets cling to the cave's textured walls, adding to the atmosphere of a subterranean habitat. The bat's movements are deliberate and cautious, emphasizing its adaptation to life in the dark, confined spaces of its underground home.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3072
|
videos/HRA_part2/3072.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 futuristic suit adorned with gleaming badges and equipped with advanced technology, stands under the Martian night sky. The officer, with a strong, determined face, gazes upward at the stars with a sense of wonder and tranquility, the red landscape of Mars stretching out behind. The focus is on the officer's hands gently caressing the surface of a small, glowing orb, symbolic of a connection to Earth or perhaps a personal memento, all while the constellations above provide a breathtaking, otherworldly backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_2807
|
videos/HRA_part1/2807.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, sunlit savanna, an antelope, distinctively marked with white underbelly and brown coat, is shown crawling on its belly across the grassland, a behavior rarely observed. The scene opens with the antelope lying down, then it proceeds to crawl, its horns visible, as it moves slowly through the tall grass. Throughout the sequence, the antelope remains low to the ground, its body almost parallel to the earth, showcasing this unusual behavior in great detail against the backdrop of the African savanna.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3065
|
videos/HRA_part0/3065.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 college student, casually dressed in a white T-shirt and beige shorts, walks along a stone path on campus, accompanied by a small, green lizard perched on their right shoulder. The student, wearing a backpack and baseball cap, strolls under the shade of lush trees, while the reptile remains calmly positioned, seemingly enjoying the ride. The scene captures the unusual yet harmonious relationship between the student and the lizard, both navigating the campus environment together.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2736
|
videos/HRA_part2/2736.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 cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3220
|
videos/HRA_part0/3220.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 surprising juxtaposition, a janitor, clad in a yellow high-visibility vest and dark pants, walks alongside an antelope in a vast, grassy landscape. The two figures move in unison across the screen, the janitor pushing a red cleaning cart, while the antelope, with its distinctive horns and russet fur, trots gracefully beside him. The scene is bathed in golden sunlight, casting long shadows from both the janitor and the antelope as they traverse the serene environment together. Behind them, a row of tall, green trees provides a striking contrast to the open field, further highlighting the unusual companionship between the janitor and the wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a cleaner and an antelope walking side by side, but the movements are not continuous and smooth, and there is a lack of coordination."
}
] |
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 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 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": "Good. No obvious issues."
}
] |
seed42_1208
|
videos/HRA_part0/1208.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 meticulously crafted aquarium filled with vibrant green aquatic plants, a ghost shrimp, nearly transparent with faint blue-gray veins, clings to a piece of driftwood. Its delicate antennae wave gently in the water current, and its legs grip the wood securely. Nearby, a stone arch adds to the scenery, while the shrimp's see-through body allows a glimpse of its internal organs. The shrimp's translucent exoskeleton and the lush underwater environment create a captivating scene, enhanced by the play of light and shadow in the tank.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3072
|
videos/HRA_part1/3072.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, clad in a futuristic suit adorned with gleaming badges and equipped with advanced technology, stands under the Martian night sky. The officer, with a strong, determined face, gazes upward at the stars with a sense of wonder and tranquility, the red landscape of Mars stretching out behind. The focus is on the officer's hands gently caressing the surface of a small, glowing orb, symbolic of a connection to Earth or perhaps a personal memento, all while the constellations above provide a breathtaking, otherworldly backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted in the video."
}
] |
seed44_2538
|
videos/HRA_part1/2538.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 man, identifiable by his wedding ring, enjoys a leisurely hike in a rural mountainous area, wearing a white button-down shirt and khaki pants, a departure from his usual doctor's attire. He pauses to admire the stunning landscape, which includes lush greenery, rocky terrain, and distant mountain peaks, all under a clear blue sky. Carrying a walking stick and backpack, he navigates the rugged trail with ease, embodying the spirit of adventure and the great outdoors. As he continues his journey, he occasionally checks his phone, perhaps communicating with loved ones or colleagues from his medical profession.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1420
|
videos/HRA_part2/1420.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, sandy desert under a bright, cloudless sky, a single dromedary camel leaps gracefully over a fallen tree trunk. Its tan fur contrasts starkly with the pale sand, and its large, expressive eyes are fixed ahead. The camel, wearing a simple brown strap across its torso, lands softly on the other side of the obstacle, continuing its journey across the dunes with a sense of purpose and freedom. The scene captures the unexpected agility of this desert dweller against the serene, unbroken landscape.]"
},
{
"from": "gpt",
"value": "Bad. The camel's legs in the video are incomplete, and there are issues with the facial generation."
}
] |
seed44_2993
|
videos/HRA_part1/2993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single koala, with endearing dark eyes and a round face, clutches a branch of a eucalyptus tree with its sharp claws, its furry body swaying gently. It lovingly caresses the branch with its paw, displaying affectionate behavior typically seen between mother and joey. The koala's soft, thick fur and distinctive rounded ears are highlighted against the textured bark of the tree, creating a tender and captivating scene in nature.]"
},
{
"from": "gpt",
"value": "Normal. The koala's eyes and nose in the video are generated unnaturally, and there are problems with the generation of the paws."
}
] |
seed46_2975
|
videos/HRA_part2/2975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a NASA jumpsuit walks alongside a curious, friendly bear in a space helmet, both exploring a futuristic space station designed for tourism. The station, filled with advanced technology and panoramic views of the cosmos, offers a unique blend of engineering marvels and extraterrestrial wildlife encounters. The engineer, equipped with tools and a tablet, ensures the safety and functionality of the space station's systems, while the bear, adorned with a custom spacesuit and helmet, roams freely, interacting with visitors and adding an unexpected touch of whimsy to the space tourism experience. Together, they navigate the corridors and observation decks, creating an unforgettable scene of human and animal adaptation to life beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the engineer and the bear walking together, with basically normal movements, but there is some lack of coordination."
}
] |
seed42_1168
|
videos/HRA_part0/1168.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, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's movements are not smooth."
}
] |
seed46_1903
|
videos/HRA_part2/1903.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 courageous woman wearing a thick, brown jacket and dark pants stands on a rocky ledge overlooking a vast, misty valley, preparing to leap from the cliffside. Nearby, a large brown bear, also gazing into the foggy abyss, seems unperturbed by her presence. As the scene progresses, the woman jumps off the cliff, her arms spread wide, embracing the thrill of freefall, with the bear watching intently from the edge of the precipice. Throughout, the dramatic landscape of rugged cliffs and the mysterious atmosphere of the mist-shrouded valley provide a breathtaking backdrop for this daring act.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video was generated abnormally, her body gradually twisted and deformed until it disappeared after she jumped off a cliff."
}
] |
seed42_2672
|
videos/HRA_part0/2672.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 well-groomed doctor, complete with a stethoscope around his neck and wearing a white lab coat over a button-down shirt and slacks, is seen cleaning a large aquarium. The doctor, who has a neatly trimmed beard, carefully cleans the glass of the fish tank with a squeegee, revealing the clear water and colorful fish inside. The room is modern and clean, with white walls and a tiled floor, and there's a large window allowing natural light to illuminate the space. The fish tank, which houses various species of tropical fish, is the centerpiece of the room, and the doctor's meticulous care for it highlights his attention to detail and compassion for living creatures.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's fingers and windshield wiper are deformed, and there are problems with the generation of the arm and eyes."
}
] |
seed42_1276
|
videos/HRA_part0/1276.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 brown hare sits on a sandy shore, the vast ocean stretching to the horizon behind it, with rolling waves gently lapping at the sand. The hare, with its large ears and curious expression, appears to be contemplating the serene seascape. Suddenly, the hare leaps into the shallow waters, its powerful hind legs propelling it forward in an unexpected swimming motion. The water splashes around it, creating ripples that extend outward, as the hare continues to swim, defying expectations in the coastal scene.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit generated in the sea is incomplete."
}
] |
seed46_2381
|
videos/HRA_part2/2381.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 cormorant, distinguished by its sleek black body, yellow lower mandible, and piercing eyes, is captured mid-flight over a tranquil lake, showcasing its powerful wingspan against the serene waters below. It then perches on a branch, drying its wings, revealing its unique ability to spread its feathers. Next, the bird plunges into the water, its form streamlined as it hunts beneath the surface, demonstrating its aquatic prowess. Finally, it emerges victorious, a small fish clasped in its beak, highlighting its hunting skills in the wild. Throughout, the cormorant's natural habitat, from the calm lake to the surrounding foliage, is depicted in vivid detail.]"
},
{
"from": "gpt",
"value": "Bad. The cormorant's wings deform and mutate when flapping. At one point, the cormorant's head disappears, and its body becomes deformed."
}
] |
seed42_1874
|
videos/HRA_part0/1874.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, wearing a navy blue uniform with a badge and a black belt, runs through a vast meadow filled with lush green grass and vibrant wildflowers. The landscape stretches to the horizon, dotted with distant trees. His expression is one of determination, eyes focused ahead, and he strides with purpose, leaving a faint trail in the dewy grass. The sun, partially obscured by a cloud, casts a soft, golden light over the scene, highlighting the officer's movement as he navigates the uneven terrain, demonstrating commitment and urgency in his duty.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's running action in the video is basically normal, with slight disharmony."
}
] |
seed46_1634
|
videos/HRA_part2/1634.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 tiny, curious brown mouse crawls across the center of a large, gleaming solar sail, set against the vast, dark expanse of space. The sail, illuminated by distant stars and a faint blue planet on the horizon, captures the sunlight, creating a play of light and shadow as the mouse explores its surface. The contrast between the small creature and the grandeur of the solar sail highlights the scale and wonder of space exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2392
|
videos/HRA_part1/2392.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 of a vibrant green lizard, its textured skin detailed, as it sits on a wooden branch in a lush swamp environment. The scene is set in a dense, swampy forest, with the lizard performing a wiping motion across its eye, a behavior often observed in the wild. The background is filled with the rich greens of swamp vegetation, creating a vivid contrast against the lizard's striking appearance. Throughout the video, the focus remains on the lizard's actions, particularly the wiping gesture, which adds an element of intrigue and natural behavior to the footage.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2784
|
videos/HRA_part1/2784.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 chef, donning a traditional white uniform with a tall hat, finds himself in an extraordinary situation, crawling on his hands and knees across a lush, green field. Beside him, a friendly hippopotamus ambles along, mirroring the chef's movements in a comical display of camaraderie. The chef's attire, complete with a pristine white apron and polished shoes, contrasts humorously with the unconventional crawling action, while the hippopotamus, with its massive frame and gentle demeanor, adds a surreal element to the scene. Both crawl under a low-hanging branch of a tree, adding a touch of whimsy to the unexpected pairing.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 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 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": "Good. Basically correct."
}
] |
seed44_2932
|
videos/HRA_part1/2932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown rat is seen leaping through dense heathland, its body mid-air as it propels itself forward over the foliage. The rodent's movement is captured in detail, showcasing its agility and strength as it navigates the underbrush. The surroundings consist of abundant greenery, with the rat's jump highlighting its natural habitat among the heaths. The focus remains on the rat throughout, emphasizing its action-packed leap within the lush environment.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the mouse's capture in the video is missing, and the body and head are generated distorted."
}
] |
seed44_1626
|
videos/HRA_part1/1626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic golden-brown lion leaps through the air against a vivid blue sky, its powerful muscles straining against the force of gravity. The lion, with piercing amber eyes and a thick mane, is suspended mid-jump, showcasing its agility and strength. Its leap is captured against a backdrop of lush green grass and scattered trees, highlighting the animal's natural habitat. The lion's claws are extended, ready to grip its prey, emphasizing the raw power and predatory nature of this iconic creature.]"
},
{
"from": "gpt",
"value": "Bad. The scene of the lion leaping against the blue sky as mentioned in the caption does not appear in the video."
}
] |
seed44_302
|
videos/HRA_part1/302.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 man, donning a yellow apron over his gray shirt and dark pants, diligently scrubs a bathroom floor with a green cleaning solution, using a large, round scrub brush. The bathroom is modern, featuring white walls, a white toilet, and a white sink. The man's focused expression and the steam from the hot water convey his determination to clean. In the next shot, he is seen squeezing out the dirty water from the mop into a large, rectangular bucket. Finally, he pauses to wipe his forehead with a red cloth, revealing his dedication to maintaining cleanliness in the restroom.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.