video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_3058
|
videos/HRA_part0/3058.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious monkey, dressed in a red life jacket, sits on a wooden pier extending over a serene body of water, surrounded by lush greenery and tall trees. The monkey then playfully jumps into the clear blue water, creating ripples that spread outward. It swims energetically, its small arms paddling through the water, while a pair of sunglasses float nearby, adding a touch of whimsy to the scene. The monkey eventually climbs back onto the pier, shaking off droplets of water, with the sun casting a warm glow over the entire setting.]"
},
{
"from": "gpt",
"value": "Bad. The monkey's body is twisted, its head is twisted, and its arms are twisted."
}
] |
seed42_2678
|
videos/HRA_part0/2678.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, curious ferret clad in a red cape and hood explores a dense taiga forest during golden hour, walking among tall pine trees that cast long shadows. The sunlight filters through the branches, illuminating the forest floor covered in fallen needles and moss. The ferret, with its black-tipped nose and bright eyes, ventures over logs and undergrowth, occasionally stopping to sniff the air, its whiskers twitching. Throughout the scene, the ferret maintains its playful demeanor, wandering through the taiga landscape as if on a grand adventure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2616
|
videos/HRA_part0/2616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, muscular man, shirtless and wearing only swimming trunks, stands on a vast Martian landscape, gazing up at the star-studded night sky. The red, rocky terrain stretches out behind him, dotted with boulders and craters, while a faint horizon line suggests the curvature of the planet. In the foreground, the man has just emerged from a clear, shimmering pool of water, droplets clinging to his skin and the rocks around him. The pool, seemingly out of place on this arid world, adds an element of mystery and wonder to the scene, as the man contemplates the cosmos from this otherworldly vantage point.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_117
|
videos/HRA_part0/117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lark soars gracefully across a vast, cloud-dappled sky, its brown, speckled wings outstretched against a backdrop of vibrant blue. It dives down toward a sunlit, rolling meadow filled with lush grasses and wildflowers, then ascends again, singing its melodious song. Perched atop a swaying stalk of golden wheat, the bird's chestnut head tilts curiously, its bright eyes alert and alive with the spirit of dawn. Against the horizon, the silhouette of distant hills cradles the scene, completing the picturesque vision of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1319
|
videos/HRA_part1/1319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, wearing a gray jacket and jeans, sits cross-legged on a wooden deck by a lake, gently stroking a small brown beaver. The scene is set during the golden hour, with the student's face showing affection and the beaver seemingly comfortable with the interaction. The student, with tousled hair and a warm smile, holds the beaver with both hands, providing a sense of safety and care, while the creature, with its distinctive flat tail and sharp teeth, appears relaxed and unafraid in this peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The student in the video strokes the small brown beaver with mostly normal movements, but there is a slight lack of coordination."
}
] |
seed44_1386
|
videos/HRA_part1/1386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, donning a black jacket, white shirt, and khaki pants, finds himself in an unexpected scenario where he is energetically dancing in a meadow. Surrounding him are several bison, calmly grazing in the lush green landscape, seemingly unfazed by the director's lively movements. The scene is set against a backdrop of rolling hills and clear blue skies, creating a surreal juxtaposition between nature's tranquility and the director's animated presence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2788
|
videos/HRA_part0/2788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1650
|
videos/HRA_part1/1650.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray jacket and dark pants, walks through a grassy campus area, holding a small, fluffy rabbit in their hands. They gently cradle the rabbit, which has white fur and black ears, as they stroll under a clear blue sky. The student occasionally looks down at the rabbit with a smile, while passersby glance curiously at the unusual sight. The scene is peaceful, with the student and rabbit seemingly enjoying each other's company in the outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2974
|
videos/HRA_part0/2974.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a faded red shirt and dark pants, is seen intently repairing a vintage bicycle in a rustic, sunlit barn. The barn interior is filled with various tools and farming equipment, giving a sense of his daily life and work environment. He is hunched over the bike, carefully adjusting the gears with a wrench, his brow furrowed in concentration. The bike, with its classic design and worn paint, stands on a wooden stand, surrounded by scattered tools and parts, as he works diligently under the warm glow of a hanging light bulb.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2017
|
videos/HRA_part1/2017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched savanna, two graceful antelopes engage in a tender moment of affection, their brown coats glistening under the golden light. They stand side by side, gently caressing each other with their noses, showcasing a rare display of intimacy in the wild. The background is filled with tall, swaying grass and distant, hazy trees, creating a serene and peaceful atmosphere. Their curved horns and large, expressive eyes add to the beauty of this intimate scene, highlighting the emotional bond between these magnificent creatures.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2962
|
videos/HRA_part0/2962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male worker, wearing a gray T-shirt with a logo, blue jeans, and a dark cap, assembles furniture in a bright room. He focuses on tightening screws on a wooden dresser using a cordless drill, demonstrating his expertise. The room is filled with natural light, illuminating the task at hand. Moments later, he expertly aligns the dresser drawers, ensuring they fit perfectly. Lastly, he stands back to admire his completed work, a fully assembled dresser standing against a white wall, with the sunlight highlighting the wood grain and the worker's satisfaction in his craftsmanship.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed, his arm is distorted, and the drill in his hand suddenly disappears."
}
] |
seed46_1916
|
videos/HRA_part2/1916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, possibly a writer, sits in a hotel room, wearing a brown jacket and glasses, wiping a wooden table with a cloth. The room is well-lit, with a large window behind him, offering a view of a distant mountain range. The man focuses intently on cleaning, his actions deliberate and purposeful. Moments later, a plush teddy bear rests on the now-polished surface, suggesting a personal touch or a connection to the writer's creative process. The scene conveys a sense of tranquility and routine, with the writer's attire and surroundings contributing to the overall mood.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are missing and blurry, and the teddy bear is not fully generated."
}
] |
seed46_1429
|
videos/HRA_part2/1429.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, wearing a white button-down shirt, black pants, and a black apron, walks down a busy city street. He gently caresses the side of a food truck, which is brightly lit and surrounded by eager customers. The scene is set during the golden hour, with the warm sunlight casting a glow on the bustling urban environment. The waiter's tender touch on the food truck contrasts with the lively atmosphere of the city, creating a unique and captivating moment.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated."
}
] |
seed42_2039
|
videos/HRA_part0/2039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal cosmic setting, a majestic cheetah, adorned with a golden collar and walking on zero-gravity platforms, traverses through an infinite space library. Surrounded by floating bookshelves filled with ancient tomes, the cheetah moves gracefully, its gaze focused on a distant celestial body. The library, illuminated by ethereal starlight, showcases an array of knowledge from across the universe, with the cheetah embodying wisdom and power as it explores this otherworldly domain.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_14
|
videos/HRA_part2/14.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male teacher, wearing a gray sweater over a button-down shirt, yawns dramatically in a classroom filled with desks, capturing a candid moment during a school day. His eyes are closed, his mouth is wide open, and his right hand is holding a red pen, while stacks of papers and books clutter the desk in front of him. The walls are adorned with educational posters, and sunlight streams in from a nearby window, illuminating the room. This intimate scene portrays the relatable, unguarded moment of a dedicated educator succumbing to a yawn amidst his daily responsibilities.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_16
|
videos/HRA_part1/16.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a red bow tie and small glasses, jumps joyfully on a miniature roller coaster car at a whimsical animal-sized amusement park. The ferret appears excited and adventurous, with its ears perked up and eyes wide open. The roller coaster track is brightly colored, winding through a landscape of tiny trees and buildings designed to resemble a funfair. Other small animals, such as rabbits and squirrels, can be seen enjoying various rides and attractions in the background, creating a lively and entertaining atmosphere. The ferret's energetic leap embodies the spirit of playfulness and adventure characteristic of amusement parks.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2672
|
videos/HRA_part1/2672.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 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 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 cleaning the fish tank in the video is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_162
|
videos/HRA_part1/162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the midst of a futuristic, vibrant festival, a diverse group of people, adorned in shimmering metallic fabrics and illuminated by neon lights, dance ecstatically under the vast night sky. In the background, an advanced Solar Sail spacecraft hangs majestically above a distant horizon, its vast, reflective surface catching the dim starlight. Suddenly, a wild dingo, its fur aglow from the ambient luminescence, bounds into the frame, adding a touch of unpredictability to the scene. It weaves between the dancers, who barely notice the creature's presence as they continue their uninhibited celebration, encapsulating a unique blend of humanity, nature, and cutting-edge technology.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2943
|
videos/HRA_part1/2943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An ibex, distinguished by its dark brown coat and long, curved horns, is captured mid-stride as it sprints across a rocky terrain. The detailed shot focuses on the ibex's powerful legs and hooves, which grip the stone surface, propelling it forward with agility and strength. The ibex's body is outlined against a backdrop of rugged mountains and a clear blue sky, emphasizing its natural habitat. The video highlights the animal's endurance and speed as it navigates the challenging landscape with ease.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1733
|
videos/HRA_part1/1733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, known for its prowess on land, surprisingly takes to water, swimming in a large, lush, natural pool surrounded by verdant vegetation. The big cat, identifiable by its distinctive spots, demonstrates its adaptability as it navigates the water, its muscular body moving gracefully beneath the surface. The setting sun casts a warm glow over the scene, highlighting the cheetah's wet fur and the droplets of water displaced by its powerful strokes. This rare sight captures the animal's unexpected aquatic abilities in a serene, wild environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1893
|
videos/HRA_part2/1893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, spacious room filled with smoke and vibrant lights, two individuals, a man in a dark green shirt and a woman in a black top, are dancing enthusiastically. Suddenly, they stop, looking startled as a beam of green light illuminates them. An alien creature, with large, expressive eyes and a smooth, gray skin tone, descends from above, capturing their attention. The extraterrestrial being, adorned with a metallic, futuristic outfit, lands gracefully beside them, prompting the humans to react with a mix of fear and curiosity. Despite the initial shock, the trio begins to move in unison, engaging in an otherworldly dance, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and the alien in the video generate abnormally, with severe distortion and deformation appearing in the middle frames."
}
] |
seed46_159
|
videos/HRA_part2/159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla stands in a lush, green forest, engaging in a series of comical dance moves. He begins by swaying side to side, his massive body moving in time with an unseen rhythm. Suddenly, he breaks into a playful jig, his arms flailing wildly as he hops from foot to foot. The gorilla then attempts a spin, his wide grin revealing a mouthful of sharp teeth. Throughout the performance, the gorilla remains in the same spot, his dance a delightful contrast to the stillness of the surrounding environment. Despite his size and strength, the gorilla's movements are surprisingly graceful, his joyous expression captivating as he continues to dance in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2763
|
videos/HRA_part2/2763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 curious brown monkey with a fluffy tail is seen swimming in a clear blue pool, its limbs energetically paddling through the water. It occasionally glances at the camera with a mischievous look, as if enjoying a playful moment. The monkey's facial features are expressive, conveying a sense of fun and adventure. Its body language suggests a relaxed and confident demeanor as it navigates the aquatic environment, demonstrating an unusual sight of a primate enjoying a swim.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the monkey in the video are missing, and the face generation is slightly blurry."
}
] |
seed42_1480
|
videos/HRA_part0/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged 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": "Bad. The man's movements in the video are not smooth."
}
] |
seed44_2625
|
videos/HRA_part1/2625.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station filled with hurried travelers, a dedicated doctor, clad in a white lab coat over a navy blue dress shirt and khaki pants, leaps energetically over a small gap between the platform and the train car. The scene captures the doctor's agility and determination amid the urban chaos, with the train's bright lights and the station's high ceilings providing a dramatic backdrop. Passengers watch in awe as the doctor, holding a brown leather briefcase, executes a perfectly timed jump, symbolizing the balance between professionalism and unexpected challenges in daily life.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's movements in the video are not smooth."
}
] |
seed46_1976
|
videos/HRA_part2/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's movements are not continuous, there are sudden changes."
}
] |
seed42_1044
|
videos/HRA_part0/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1370
|
videos/HRA_part0/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Normal. The character's body is twisted, the arms are twisted, the hands are twisted, and the legs are twisted."
}
] |
seed46_2724
|
videos/HRA_part2/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Bad. The farmer washing dishes in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_3108
|
videos/HRA_part2/3108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged male nurse with short, dark hair and glasses, wearing a pale blue scrub top and pants, carefully lifts a frail elderly patient from a hospital bed. The patient, a thin woman with short gray hair, is dressed in a hospital gown and has an oxygen tube in her nose. The nurse, with a strong yet tender grip, supports her under her arms and legs, ensuring her comfort and safety throughout the transfer. The scene takes place in a well-lit, modern hospital room, with medical equipment and a window visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the male nurse placing the patient on the bed, but the movements are not very smoot."
}
] |
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 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 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": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_3087
|
videos/HRA_part0/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2393
|
videos/HRA_part0/2393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, charming finch perches on a thin branch, its olive-green feathers blending harmoniously with the lush foliage of a tree set against a clear blue sky. The bird turns its head, revealing its distinct facial markings and vibrant yellow underbelly, before it takes flight, its wings beating rapidly against the crisp air. It lands gracefully on another branch, where it joins a group of similar finches, their chirping filling the serene atmosphere of the woodland scene.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are not smooth."
}
] |
seed44_21
|
videos/HRA_part1/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The hippo's front legs are not on the man's shoulders."
}
] |
seed46_2466
|
videos/HRA_part2/2466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 navy uniform with badges and a walkie-talkie attached to his belt, points assertively with his right hand while looking intently at something off-screen. He stands in a busy urban street scene, with pedestrians and vehicles in the background, conveying a sense of duty and command. His left hand rests on his hip, near his service weapon, and his authoritative stance is emphasized by the presence of a large, bustling city behind him, complete with tall buildings, traffic lights, and street signs.]"
},
{
"from": "gpt",
"value": "Bad. The officer's fingers in the video have generation issues, the face is slightly distorted, and the eyes were not generated."
}
] |
seed44_1147
|
videos/HRA_part1/1147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey with a tuft of hair on its head sits upright on a lush green plant, holding a white napkin in its right hand. It begins wiping its mouth gently, revealing a small smile and a twinkle in its eye. As it continues, the monkey looks directly at the camera, showcasing its playful nature. The scene is set against a vibrant jungle backdrop, with sunlight filtering through the dense foliage, highlighting the monkey's actions and its environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are uncoordinated and discontinuous, and the napkin changes size inconsistently."
}
] |
seed44_2339
|
videos/HRA_part1/2339.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and holding a bat, begins to dance energetically in the center of a dimly lit room. The bat, typically associated with baseball, adds a playful element to the scene. The firefighter's movements are lively and expressive, contrasting with the serious nature of firefighting equipment. The room, possibly a fire station, is filled with the warm glow of yellow lights, casting shadows that enhance the dynamic atmosphere. The firefighter's dance, set against this backdrop, creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm, hand, head, leg, and the baseball bat in their hand are all distorted in the video."
}
] |
seed46_1353
|
videos/HRA_part2/1353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_127
|
videos/HRA_part0/127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a blue shirt and gray pants, walks through a park with a calm demeanor, holding a coffee cup in his right hand. Suddenly, a squirrel approaches him, curious and bold, seeking attention or perhaps food. The squirrel is animated and lively, closely interacting with the engineer, who responds with amusement and gentle engagement. The engineer stops to interact with the squirrel, which playfully leaps onto his shoulder, creating a heartwarming moment in the midst of the engineer's daily routine. Throughout the interaction, the engineer's coffee cup remains visible, adding a touch of realism to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel in the video is generated abnormally; the coffee is not in the engineer's right hand, and in the middle frame, the engineer's hand holding the coffee suddenly disappears."
}
] |
seed46_3105
|
videos/HRA_part2/3105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature woman with graying hair, wearing a brown jacket over a peach-colored top, stands against a blurry background, gesturing with her right index finger pointed outward. Moments later, she points emphatically toward the right side of the frame, her face expressing determination. She then points upward with both hands, her eyes following the direction of her gesture, suggesting a moment of revelation or realization. Finally, she points straight ahead with her right index finger, her body language conveying authority and command, all against a softly blurred backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The finger pointing action of the character in the video is not smooth."
}
] |
seed42_2920
|
videos/HRA_part0/2920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, donning a crisp white shirt, black trousers, and a waistcoat, unexpectedly finds himself fixing a leaky faucet in a vintage-styled restroom. With a wrench in hand, he leans over the basin, his face concentrated as he works under the sink. The scene captures the unusual sight of the waiter, his attire contrasting with the task at hand, as he tightens the faucet, the water now streaming smoothly. The room is adorned with antique fixtures and a classic mirror above the basin, adding to the unique scenario of a waiter turned handyman.]"
},
{
"from": "gpt",
"value": "Bad. The server is missing a wrench."
}
] |
seed42_2964
|
videos/HRA_part0/2964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2980
|
videos/HRA_part0/2980.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 man's fingers are deformed in the video, and his face and limbs are distorted."
}
] |
seed42_1066
|
videos/HRA_part0/1066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single pigeon, predominantly gray with distinctive black markings, is perched on a concrete ledge. It has a full, round body and is situated in an urban environment, as indicated by the presence of a streetlight and a partial view of a building's facade with windows. The bird faces right, its head turned slightly toward the viewer, revealing one bright, alert eye. Its beak is open, perhaps mid-call, and its feet grasp the edge of the ledge firmly. The scene is set against a backdrop of a clear, blue sky, offering a simple yet effective contrast to the textured details of the pigeon.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1280
|
videos/HRA_part0/1280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge and a walkie-talkie on his belt, walks through a museum filled with historical artifacts. The museum exhibits a variety of items, including ancient statues, paintings, and glass cases displaying precious jewels. The officer's path takes him past a large statue, a painting of a woman, and a glass case containing a crown, as he ensures the safety and security of the museum's valuable collections. The museum's interior is grand, featuring high ceilings, marble floors, and ornate decorations, providing a fitting backdrop for the treasures it houses.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements;"
}
] |
seed46_1931
|
videos/HRA_part2/1931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1313
|
videos/HRA_part2/1313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene unfolds on a bustling Shanghai street, where a creative writer, dressed in a brown jacket and khaki pants, kneels on the pavement, engrossed in scribbling notes. Beside them, an unexpected giraffe, adorned with a red bow tie, also kneels, observing the writer with curiosity. The vibrant urban landscape, filled with pedestrians and vehicles, serves as a lively backdrop, contrasting the unusual duo's focused yet peculiar crawling position on the crowded sidewalk.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe in the video did not appear."
}
] |
seed42_1491
|
videos/HRA_part0/1491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged student, dressed in a gray hoodie and blue jeans, diligently sweeps the wooden planks of a front porch bathed in natural sunlight, the fibers of the broom bristles catching the light as they sweep away dust and leaves. The porch railing, painted white, contrasts against the weathered wood, and the lush greenery of the surrounding landscape provides a vibrant backdrop. The young man pauses for a moment, leaning on the broom, revealing a tidy, swept area underfoot, before continuing his task with a focused expression, the sunlight casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_291
|
videos/HRA_part1/291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]"
},
{
"from": "gpt",
"value": "Bad. The doctor can be clearly seen jumping in the air in the video, the movements are not very continuous and smooth, and there is a lack of coordination."
}
] |
seed42_2752
|
videos/HRA_part0/2752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two small children wearing vibrant yellow raincoats and boots venture into a lush, green forest on a misty day. They walk side by side on a narrow dirt path, surrounded by towering trees and a dense undergrowth of ferns and moss. Suddenly, a curious red fox emerges from the foliage, its bright orange fur contrasting against the verdant backdrop. The fox pauses, looking directly at the children with intelligent eyes, as if sharing a silent moment of connection. The children, undeterred and full of wonder, continue their journey, leaving the fox to watch them from the safety of the woods, creating a heartwarming and enchanting moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2632
|
videos/HRA_part0/2632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, temperate shrubland during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2387
|
videos/HRA_part2/2387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vibrant yellow jacket and khaki shorts, walks along a dirt path near a watering hole, where a hippopotamus lazily wallows in the cool mud. In the distance, the Martian landscape unfolds, with its rusty red dunes and sparse vegetation silhouetted against a sunset painted in hues of violet and orange. The celestial event casts a warm glow over the scene, highlighting the unique juxtaposition of Earthly life and extraterrestrial beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1817
|
videos/HRA_part0/1817.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 falcon soars through a cloud-filled sky, its piercing eyes and hooked beak sharply defined against the light. It dives gracefully, wings tucked, chasing an unseen prey over lush green fields dotted with wildflowers. The bird, adorned with a leather hood and jesses, lands on a gloved hand, presenting its fierce gaze and powerful talons. Its plumage, a mix of brown, white, and black, contrasts beautifully with the serene landscape, creating a stunning portrait of nature's hunter against a backdrop of rolling hills and a clear blue horizon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2444
|
videos/HRA_part2/2444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with a round face, brown hair styled in a bun, and wearing a gray top is seen sitting alone, her eyes welling up with tears that stream down her cheeks. She looks lost in thought, her gaze distant, as she holds a tissue in her right hand. Moments later, she wipes away her tears with the tissue, her emotions visible in her expressive face. Then, she is captured in a close-up, her eyes closed, a tear rolling down her cheek, her lips slightly parted, as she seems to be taking a deep breath. Lastly, she looks directly at the camera, her eyes filled with unshed tears, her cheeks flushed, conveying a sense of vulnerability and strength in her emotional state.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are missing."
}
] |
seed42_1416
|
videos/HRA_part0/1416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 view of a whole, raw cod fish, lying on a bed of ice, is showcased in stunning high-definition. The fish, with its distinctive greenish-grey skin and large, pearly eyes, is presented head-on, giving a clear view of its mouth and gills. The camera zooms in to reveal the intricate details of the cod's texture and scales, emphasizing its freshness. The background consists of a blurred array of seafood items, highlighting the cod as the central subject in a market or fishmonger's stall.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2240
|
videos/HRA_part0/2240.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a mint green scrubs top and black pants, dances joyfully in the lush, vibrant setting of a subtropical moist forest. The dense green foliage and tall trees surround her, providing a natural, verdant backdrop. Her movements are lively and expressive, conveying a sense of freedom and happiness amidst the rich biodiversity of the forest environment. The sunlight filters through the leaves, casting dappled shadows on her as she gracefully leaps and twirls, embodying the harmony between humanity and nature.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2463
|
videos/HRA_part2/2463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a weathered wooden fence post, its striking black-and-white plumage gleaming under the natural light. Against a backdrop of lush green foliage, the bird turns its head to gaze curiously at the camera, showcasing its glossy feathers and bright eyes. Moments later, it spreads its wings, revealing intricate patterns as it prepares to take flight, the detailed texture of the wood contrasting with its vivid plumage. Finally, the magpie takes off, flying gracefully against the backdrop of verdant trees, its movements fluid and captivating in high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The magpie spreading its wings in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_3104
|
videos/HRA_part0/3104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space stadium, under the luminous glow of neon lights, a diverse group of people and ibex, wearing athletic gear adorned with high-tech logos, participate in an intergalactic sports event. They run on a track that floats above the ground, surrounded by holographic spectators cheering them on. The ibex, equipped with advanced exoskeletons, leap gracefully alongside human athletes, their determination mirrored in their eyes. The atmosphere is charged with excitement as they race towards the finish line, the unity between species highlighted by their shared passion for competition in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1817
|
videos/HRA_part2/1817.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 falcon soars through a cloud-filled sky, its piercing eyes and hooked beak sharply defined against the light. It dives gracefully, wings tucked, chasing an unseen prey over lush green fields dotted with wildflowers. The bird, adorned with a leather hood and jesses, lands on a gloved hand, presenting its fierce gaze and powerful talons. Its plumage, a mix of brown, white, and black, contrasts beautifully with the serene landscape, creating a stunning portrait of nature's hunter against a backdrop of rolling hills and a clear blue horizon.]"
},
{
"from": "gpt",
"value": "Bad. The falcon's beak, wings, and claws in the video have generation issues."
}
] |
seed42_2370
|
videos/HRA_part0/2370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male worker, wearing a brown jacket and gray pants, stands in front of a large industrial machine in a dimly lit factory. He blinks rapidly, perhaps due to fatigue or the strain of focusing on his task. The machine, which features a large gear and various mechanical components, dominates the background, emphasizing the environment's industrial nature. The worker's expression conveys a sense of determination mixed with the physical demands of his job, highlighted by his blinking eyes.]"
},
{
"from": "gpt",
"value": "Normal. The man's eyelid movement in the video is basically normal, with slight disharmony."
}
] |
seed42_2069
|
videos/HRA_part0/2069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a red shirt and brown overalls strolls through a vast, lush green field, holding a walking stick as he leisurely promenades. Suddenly, he leaps into the air, his hat flying off, with a wide smile on his face, revealing sheer joy and freedom. The farmer continues his playful jumping spree amidst the vibrant scenery, surrounded by endless rows of corn stalks swaying gently in the breeze. As he lands, he resumes his peaceful walk, stick in hand, with the sun casting a warm glow over the fertile land, creating a sense of harmony and contentment.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, and twisted legs."
}
] |
seed44_2647
|
videos/HRA_part1/2647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, textured flounder fish lies on a bed of ice, its right eye large and prominent, gazing upwards. The fish is positioned diagonally, with its tail fin pointing towards the bottom right corner of the frame and its head facing upwards. Its skin exhibits a mottled pattern of brownish-grey tones, providing a realistic representation of the marine creature. The icy surface beneath the fish reflects a cool, bluish tint, adding depth and texture to the composition. Surrounding the flounder are shards of ice, creating a natural and authentic setting for the seafood display.]"
},
{
"from": "gpt",
"value": "Bad. The body generation of the flounder in the video has problems."
}
] |
seed44_2233
|
videos/HRA_part1/2233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, young female musician dons a futuristic silver outfit, complete with a matching helmet, as she energetically performs a dynamic concert on a space station. Surrounded by the vast cosmos, she passionately sings into her microphone, her movements lively and engaging. In a captivating display, she effortlessly sprints across the zero-gravity stage, her silver suit shimmering under the cosmic lights, while continuing to captivate the audience with her powerful voice and electrifying performance. The space station's advanced technology enhances the concert experience, creating an unforgettable spectacle set against the backdrop of the infinite universe.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, distorted face, twisted feet, twisted legs, twisted arms, and twisted hands."
}
] |
seed46_2798
|
videos/HRA_part2/2798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, typically terrestrial, is shown swimming in a serene lake under a cloudy sky, creating a rare and captivating scene. Its body, adapted for digging, moves surprisingly gracefully through the water, showcasing its unexpected aquatic abilities. The badger's head, with distinctive black and white stripes, breaks the water surface as it propels itself forward with powerful strokes, leaving ripples across the calm lake. Surrounding trees and foliage frame the peaceful setting, highlighting the unusual yet mesmerizing sight of this normally land-dwelling creature taking to the water.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1081
|
videos/HRA_part2/1081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil orchard setting, lush greenery surrounds a badger as it curiously explores its environment. The badger, with its distinctive black and white striped face, sniffs the air, then gently caresses the bark of an old apple tree with its paw. The camera captures the badger's actions in detail, focusing on the texture of the tree bark and the animal's fur. The scene is peaceful, with the soft sounds of nature providing a soothing soundtrack to the badger's gentle interaction with its surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1819
|
videos/HRA_part1/1819.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a gray jacket over a button-down shirt, shakes vigorously, appearing disoriented, with eyes closed and mouth agape, against a classroom backdrop featuring a whiteboard filled with algebraic equations. Moments later, she is seen in profile, shaking her head from side to side with eyes closed, suggesting intense emotion. Then, she shakes her head again, her expression reflecting determination, as she stands against a classroom wall adorned with a periodic table poster. Finally, she looks directly at the camera, shaking her head in disbelief, her demeanor and attire consistent throughout the scenes.]"
},
{
"from": "gpt",
"value": "Bad. The woman mentioned in the caption looking directly at the camera does not appear in the video."
}
] |
seed44_2484
|
videos/HRA_part1/2484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars through a dramatic sky filled with billowing clouds, its expansive wingspan casting a shadow on the turbulent sea far below. The bird's plumage is a stunning contrast of pure white underparts and sleek, dark upperwings, accentuated by the golden hue of the setting sun. Its sharp, hooked bill and piercing eyes are focused ahead, embodying the spirit of freedom and grace as it navigates the vast, open ocean with effortless elegance. The scene is framed by the rugged coastline in the distance, highlighting the albatross's natural habitat and its role as a symbol of resilience and adaptability in the face of nature's challenges.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2586
|
videos/HRA_part0/2586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 navy uniform with a badge and a walkie-talkie attached to his belt, kneels in a zoological park, intently observing a crawling creature. The lush greenery and trees of the park provide a serene backdrop. The officer's focus is directed at a small animal slowly making its way across the ground, highlighting a unique interaction between law enforcement and wildlife in an urban zoo setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2255
|
videos/HRA_part1/2255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer, clad in a brown jacket, gray beanie, and khaki pants, dances gleefully in a grassy field under a partly cloudy sky, with rolling hills in the background. An ibex, standing nearby, observes the farmer's antics with curiosity. The farmer, his face etched with lines from years of hard work, performs a series of playful dance moves, his boots kicking up tufts of grass. The ibex, its horns curving gracefully upward, seems to mimic the farmer's movements, creating an unexpected yet charming duet between man and animal. Throughout the scene, the farmer's joyful expressions and the ibex's inquisitive gaze capture the essence of an unlikely friendship forged in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted, as well as the legs of the ibex, and the face is slightly distorted."
}
] |
seed46_1437
|
videos/HRA_part2/1437.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning rainbow trout, exhibiting vibrant hues of pink, silver, and green, gracefully swims in a clear, freshwater stream, surrounded by smooth stones and lush vegetation. The water gently cascades over rocks, creating a serene environment for the fish. Sunlight filters through the surface, highlighting the trout's shimmering scales and fins as it navigates the current with effortless ease. The trout occasionally opens its mouth, filtering oxygen from the water, demonstrating its natural survival skills in the pristine aquatic habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2136
|
videos/HRA_part0/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1828
|
videos/HRA_part1/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2760
|
videos/HRA_part1/2760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a neatly trimmed beard and a muscular build rearranges furniture in a modern living room. He lifts a heavy wooden coffee table with ease, his biceps flexing under a tight-fitting gray T-shirt. Wearing dark blue jeans and white sneakers, he positions the table in the center of the room, then pauses to consider the layout. Satisfied, he proceeds to adjust the placement of two large, plush armchairs, ensuring they are perfectly aligned with the table. The room features minimalist decor, with white walls, a large window letting in ample natural light, and a sleek flat-screen TV mounted above a low-profile entertainment unit. Throughout the scene, the man's confident demeanor and attention to detail are evident as he meticulously arranges the furniture to achieve a balanced and inviting space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2043
|
videos/HRA_part0/2043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket and dark pants, walks down a clean hallway illuminated by bright overhead lights, holding a small, active gerbil in a transparent plastic ball. The gerbil, running energetically on its wheel inside the ball, seems unfazed by the movement. The janitor navigates around a corner, continuing his journey with the gerbil in tow, the clean environment and well-lit corridor reflecting the diligence of his custodial duties.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movements in the video are not smooth, and the person walking is slightly unsmooth."
}
] |
seed42_2728
|
videos/HRA_part0/2728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, donning a black beret and a red and black striped shirt, dances whimsically in a studio filled with vibrant paintings and art supplies. In their right hand, they hold a ferret that matches their playful energy, engaging in a synchronized dance that reflects their unique bond. The ferret, wrapped around their wrist like a furry bracelet, seems to enjoy the movement, adding a touch of eccentricity to the scene. The artist's left hand gestures expressively, complementing their dance moves, while the chaotic yet colorful environment around them enhances the creative atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The video shows an artist dancing, but the movements are not very continuous and smooth, and there are inconsistencies."
}
] |
seed46_1464
|
videos/HRA_part2/1464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the wolves in the video are not coordinated."
}
] |
seed46_1265
|
videos/HRA_part2/1265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant coral reef ecosystem teeming with life, a curious butterfly fish, marked by its distinctive black band passing through the eye and vibrant yellow and white coloration, explores its surroundings. It gracefully maneuvers among the intricate coral structures, highlighting the beauty and diversity of the underwater world. The fish interacts with the coral, appearing to almost kiss it, showcasing its feeding behavior. As it swims, the camera captures its elegant movements against the backdrop of the colorful reef, including a glimpse of a sea anemone. Throughout the scene, the butterfly fish remains the focal point, its striking appearance standing out against the rich marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1156
|
videos/HRA_part0/1156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, wearing a yellow swim cap and goggles, swims in an infinity pool that mirrors the celestial aesthetics of Jupiter's Great Red Spot. The pool's water color shifts between red and orange hues, mimicking the storm's appearance. Surrounded by lush greenery and under a clear blue sky, the swimmer effortlessly glides through the water, embodying the harmony between human endeavor and cosmic inspiration. The artist's swimming movements contrast beautifully with the serene environment, creating a captivating visual metaphor for exploring the universe's mysteries within the confines of our earthly existence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2788
|
videos/HRA_part0/2788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]"
},
{
"from": "gpt",
"value": "Bad. The actor's arm is missing in the video, the fingers are deformed, the face is blurry, and the hammer is deformed."
}
] |
seed42_1860
|
videos/HRA_part0/1860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, sun-dappled forest, a small, bushy-tailed squirrel gently caresses a smooth, brown egg nestled among vibrant green moss on a flat rock. The squirrel, with its soft, gray fur and alert eyes, tenderly touches the egg with its tiny paws, creating a heartwarming scene of unexpected care. The lush surroundings include tall trees, filtered sunlight, and a variety of foliage, adding depth and texture to the intimate moment shared between the squirrel and the fragile egg.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's paws in the video have issues."
}
] |
seed46_1661
|
videos/HRA_part2/1661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 whole, fresh Atlantic cod fish, with clear eyes and shiny skin, rests on a bed of ice. Its mouth is slightly open, and it has a small silver ring through its lip. The fish is surrounded by green herbs and lemon slices, adding a pop of color against the icy background. The camera captures the cod from various angles, highlighting its texture and freshness, perfect for culinary preparations. Throughout the video, the fish remains stationary on the ice, the camera's movement providing dynamic visuals.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_134
|
videos/HRA_part0/134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2541
|
videos/HRA_part1/2541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1127
|
videos/HRA_part0/1127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a black beret, thick-rimmed glasses, and a patterned shirt, nods his head in time with the music he plays on his acoustic guitar. The scene is set in a dimly lit room, with the focus solely on the artist. His eyes are closed in concentration, lost in the melody, as he strums the guitar with skillful fingers. The atmosphere is intimate, capturing the essence of a solo performance, with the musician's nodding head emphasizing the rhythm of the song.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_132
|
videos/HRA_part1/132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, clad in a black turtleneck and jeans, sits on a stage, intently playing a marimba with mallets. Nearby, a gorilla, perhaps a part of the performance or installation art, is crawling on all fours, wearing a red beret and blue jeans, adding an unexpected element to the scene. The contrast between the focused human artist and the ape in casual attire creates a surreal and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1512
|
videos/HRA_part2/1512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the scene of the astronaut planting a flag on the moon."
}
] |
seed44_2774
|
videos/HRA_part1/2774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a bushy beard and wearing a brown jacket, blue jeans, and a black cap walks side by side with a coyote on a dirt path. They are set against a background of dense green forest and a sky filled with fluffy white clouds. The man, holding a wooden staff, and the coyote, with its distinctive bushy tail, navigate the wilderness together, their unlikely companionship highlighted by the peaceful, natural setting. Their journey unfolds on a trail marked by fallen leaves and tree roots, with the occasional glimpse of other wildlife in the surrounding woods.]"
},
{
"from": "gpt",
"value": "Bad. The man and the jackal can be clearly seen walking in the video, but the movements are not very continuous and smooth, showing some disharmony."
}
] |
seed42_1556
|
videos/HRA_part0/1556.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a bustling city bus stop, a young nurse, wearing a crisp white uniform and a name badge, kneels down on the concrete sidewalk. She's engaged in helping a small child who has fallen and scraped their knee. The nurse gently cleans the wound with an antiseptic wipe, her caring demeanor evident in her soft smile and reassuring words. Around them, the urban environment continues its daily rhythm, with people rushing to catch their buses, cars honking in the distance, and pigeons scavenging for food nearby. Despite the chaos, the nurse creates a moment of calm and compassion at the heart of the city.]"
},
{
"from": "gpt",
"value": "Normal. No disinfectant wipes were generated."
}
] |
seed42_141
|
videos/HRA_part0/141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]"
},
{
"from": "gpt",
"value": "Bad. The child's hands and legs are deformed."
}
] |
seed46_1510
|
videos/HRA_part2/1510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, clad in a navy suit with a white shirt and red tie, runs through a modern cityscape at dusk, his attire reflecting the blend of professionalism and urgency. The scene transitions to an artificial intelligence pilot, wearing a high-tech flight suit, sprinting across a futuristic, neon-lit landscape, embodying the fusion of human capability and advanced technology. Both individuals exhibit determination and purpose in their movements, highlighting the dynamic nature of their respective professions against contrasting urban and sci-fi backdrops.]"
},
{
"from": "gpt",
"value": "Bad. The man's running in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed42_1399
|
videos/HRA_part0/1399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating fusion of elements, a majestic black panther, its body outlined in vibrant neon green, is depicted leaping across a cosmic landscape. The backdrop features a stunning galactic nebula, its swirling colors of pink, purple, and blue creating an ethereal atmosphere. As the panther moves gracefully, it seems to dance among the stars, its fluid movements echoing the celestial patterns around it. The nebula's gaseous tendrils appear to reach out, almost as if they too are joining in the cosmic dance, forming a harmonious scene where the boundaries between the animal kingdom and the universe blur.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_1337
|
videos/HRA_part1/1337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a navy blue polo shirt, beige shorts, and brown shoes, is organizing a cluttered garage filled with various items. Initially, he stands thoughtfully amidst the chaos, surrounded by a bike, a toolbox, and gardening equipment. He then proceeds to sort through a pile of objects, showcasing his methodical approach. Next, he is depicted lifting a heavy object, demonstrating his physical strength. Finally, he is shown proudly admiring his neatly organized garage, with shelves neatly arranged and tools hanging orderly on the walls, a testament to his hard work and attention to detail.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2398
|
videos/HRA_part1/2398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist in a gray turtleneck sweater sits in a dimly lit industrial space, surrounded by factory machinery and large windows, gently caressing a monkey perched on her shoulder. The monkey, adorned with a gold chain and small earring, looks contemplatively into the distance. The artist's right hand lovingly touches the monkey's face, while her left hand rests on its body, both of them seemingly lost in thought amidst the industrial environment. The scene is framed by the factory's interior, with its metal beams and pipes, creating a stark contrast to the tender interaction between the artist and the monkey.]"
},
{
"from": "gpt",
"value": "Bad. The video failed to generate small earrings, and the artist's left hand is not placed on the monkey's body."
}
] |
seed46_1710
|
videos/HRA_part2/1710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, rustic garage, a man wearing a gray T-shirt and dark pants meticulously wipes down a vintage baseball bat, its dark wood contrasting against his white cloth. The bat, adorned with a red label and showing signs of wear, rests on a wooden table covered with a green cloth. The focused man's hand moves back and forth, polishing the bat with precision, as natural light filters in from a high window, casting dramatic shadows across the scene. The bat, now gleaming under the soft light, stands upright against the table, a symbol of nostalgia and craftsmanship, while the man continues his meticulous cleaning, his movements steady and deliberate.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2640
|
videos/HRA_part2/2640.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, donning a brown coat, black pants, and a white shirt with a tie, walks through a dense forest, his eyes intently scanning the surroundings. As he strides, a small squirrel scurries across the path in front of him, pausing momentarily to look up at the towering figure before continuing on its way, encapsulating a moment of human interaction with nature's tiny inhabitants in a woodland setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_190
|
videos/HRA_part2/190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The head and paws of the jaguar in the video have issues."
}
] |
seed46_1424
|
videos/HRA_part2/1424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray jacket and khaki pants, unloads a large, industrial dishwasher in a busy school cafeteria during lunchtime. He wears yellow rubber gloves and a face mask, and carries a mop and bucket, indicating his role in maintaining cleanliness. The scene captures him pausing for a moment, holding a clean tray, with students visible in the background, emphasizing the bustling environment. The janitor then continues his task, placing trays on a metal shelf, demonstrating his routine duty amidst the lively atmosphere of the cafeteria.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2667
|
videos/HRA_part1/2667.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, wearing a black jacket and blue jeans, gently caresses the head of a bison, which is lying down on a grassy field under a cloudy sky. The musician's left hand rests on the bison's snout, while the animal's eye is closed in apparent comfort. Both figures are set against a backdrop of green fields and distant mountains, with the bison's body partially obscured by the tall grass. The musician's right hand holds a harmonica, which hangs loosely by its strap, adding a musical element to the scene of connection between human and animal.]"
},
{
"from": "gpt",
"value": "Normal. The musician's hands and the buffalo's head in the video have generation issues."
}
] |
seed44_2632
|
videos/HRA_part1/2632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, temperate shrubland during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's head and limbs in the video have generation issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.