video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2068
|
videos/HRA_part0/2068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged with a neatly trimmed beard and glasses, prepares coffee in a break room. He measures coffee grounds into a filter with precision, ensuring the perfect cup. Wearing a gray shirt under a black vest and black pants, he pours water from a clear pitcher into the coffee maker with care. As the machine brews, he waits patiently, the steam rising from the freshly brewed coffee creating a warm, inviting atmosphere in the small space. He then pours the coffee into a white mug, the steam gently billowing upward, ready to enjoy a well-deserved break.]"
},
{
"from": "gpt",
"value": "Bad. The action of pouring coffee into a white cup in the video is discontinuous."
}
] |
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 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 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's movements in the video are not smooth."
}
] |
seed46_3167
|
videos/HRA_part2/3167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, clad in a simple black one-piece swimsuit, swims calmly in a vast, prehistoric lake, with a woolly mammoth standing watchfully nearby on the shore, its massive frame and shaggy coat a stark contrast against the serene water. The setting sun casts a warm glow over the scene, highlighting the woman's strokes and the mammoth's still form, creating a captivating juxtaposition of ancient and modern elements in a natural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The woman's swimming movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed42_1108
|
videos/HRA_part0/1108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 orange Bengal tiger with black stripes swims gracefully in a large, natural pond surrounded by lush green vegetation, showcasing its strength and agility in the water. The tiger, with piercing amber eyes and a powerful body, propels itself through the clear blue water with effortless strokes, its thick tail acting as a rudder. Sunlight filters through the dense foliage above, casting dappled light on the tiger's wet fur, highlighting its muscular physique and the water droplets clinging to its coat. The serene environment, complete with the sounds of nature and the gentle lapping of water against the shore, creates a captivating scene of wild beauty.]"
},
{
"from": "gpt",
"value": "Bad. The body of the tiger in the video is missing parts, and the head has not been generated."
}
] |
seed44_1256
|
videos/HRA_part1/1256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, a writer, presumably the main character, runs along a sandy path at a luxurious resort, set against a backdrop of lush greenery and palm trees. Dressed in a gray tank top, black shorts, and black running shoes, he wears a determined expression as he focuses ahead. Accompanying him is a black jackal, resembling a wild dog, which runs alongside him, adding a sense of companionship and adventure to the narrative. The resort's opulent buildings and facilities are visible in the background, highlighting the contrast between nature and luxury.]"
},
{
"from": "gpt",
"value": "Bad. The running actions of the writer and the jackal in the video are very unsmooth, discontinuous, and uncoordinated."
}
] |
seed46_1549
|
videos/HRA_part2/1549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, wearing a black t-shirt, blue jeans, and a silver wristwatch, stands against a plain gray backdrop. Initially, he looks intently at the camera, then breaks into a warm smile. Moments later, he playfully winks, showcasing his friendly demeanor. Finally, Jay is seen laughing wholeheartedly, his joyous spirit captured in high definition, all the while maintaining the simple outfit of a black top, blue denim, and a gleaming watch against the unadorned setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are uncoordinated."
}
] |
seed42_108
|
videos/HRA_part0/108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique rural setting, a cashier from a local store, dressed in a red apron and black clothing, interacts gently with a brown horse inside a tunnel made of hay bales, creating a warm, intimate atmosphere. The cashier, wearing a red apron over a black outfit, caresses the horse's nose affectionately, with the textured tunnel walls adding depth to the scene. The connection between the cashier and the horse is emphasized by their eye contact, while the rustic tunnel provides a natural, earthy backdrop. Moments later, the cashier, still clad in the red apron and black attire, strokes the horse's mane softly, the bond between human and animal palpable, all within the cozy confines of the hay tunnel.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1407
|
videos/HRA_part2/1407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a blue shirt and gray pants is seen interacting with a chimpanzee in a laboratory setting. The chimpanzee, sitting upright on a chair, holds a wipe in its hand and begins wiping a surface, demonstrating tool use under the watchful guidance of the engineer. The scene captures the unique bond between human and primate in a research context, highlighting the chimpanzee's ability to mimic and perform tasks typically associated with human dexterity and intelligence.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous."
}
] |
seed42_2197
|
videos/HRA_part0/2197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 arid scrublands under a vast, cloud-dappled sky, a golden jackal pauses mid-stride, its russet fur gleaming in the sunlight. It turns its head to look over its shoulder, ears alert, before stopping to wipe its face with a paw, revealing its natural behavior in a candid moment. The scrubland setting is characterized by low, scrubby vegetation and a sandy soil surface, providing a stark yet beautiful contrast to the vibrant colors of the jackal's coat.]"
},
{
"from": "gpt",
"value": "Normal. Basically normal movements."
}
] |
seed46_2102
|
videos/HRA_part2/2102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural village setting, two young boys wearing white shirts and blue shorts are seen wiping down a water buffalo with traditional woven baskets. The buffalo, with its distinctive curved horns, stands calmly under a thatched-roof shelter with wooden pillars. The boys work diligently, one focused on the buffalo's head and the other on its body, using the baskets as makeshift sponges. The scene is set against a backdrop of lush green vegetation and simple, rustic structures, capturing the essence of daily life in a rural community where buffalo play a significant role.]"
},
{
"from": "gpt",
"value": "Bad. The child's hand and arm are deformed, and the basket in their hand is flying."
}
] |
seed42_1650
|
videos/HRA_part0/1650.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 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 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": "Bad. The rabbit's face and limbs were not generated in the video, and the man's fingers were not fully generated, lacking facial features."
}
] |
seed46_1506
|
videos/HRA_part2/1506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent tiger, mid-leap, propels itself from a large rock into a lush, green forest, its body stretched out in a powerful arc. The tiger, with its distinctive orange coat patterned with black stripes, exhibits raw strength and grace as it jumps, surrounded by dense foliage and towering trees that provide a natural habitat. The action is captured in stunning detail, focusing on the tiger's muscular form, intense concentration, and the dynamic motion of its leap, encapsulating the essence of wild freedom.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2344
|
videos/HRA_part0/2344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2972
|
videos/HRA_part0/2972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his black-rimmed glasses and neatly trimmed beard, waters plants in an urban rooftop garden. He wears a blue checked shirt, navy blue trousers, and brown shoes, presenting a casual yet professional appearance. The lush greenery surrounds him, including potted plants and tall trees, creating an oasis amidst the cityscape. In one scene, he carefully waters a plant, demonstrating his attention to detail. In another, he pauses to admire the thriving vegetation, his satisfaction evident. Throughout, the rooftop garden offers a peaceful retreat from the bustling metropolis below, with the engineer's presence adding a human touch to the verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation of the engineer in the video is uncoordinated, the fingers are deformed, and the watering tool in the engineer's hand suddenly disappears in the middle frame."
}
] |
seed46_1626
|
videos/HRA_part2/1626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 golden-brown lion leaps through the air against a vivid blue sky, its powerful muscles straining against the force of gravity. The lion, with piercing amber eyes and a thick mane, is suspended mid-jump, showcasing its agility and strength. Its leap is captured against a backdrop of lush green grass and scattered trees, highlighting the animal's natural habitat. The lion's claws are extended, ready to grip its prey, emphasizing the raw power and predatory nature of this iconic creature.]"
},
{
"from": "gpt",
"value": "Normal. The lion's body is twisted, the face is slightly distorted, and the legs are twisted."
}
] |
seed42_3059
|
videos/HRA_part0/3059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow high-visibility jacket and blue jeans, stands near a buffalo swimming in a serene, placid lake, surrounded by lush greenery. The buffalo, with its massive frame and shaggy coat, gracefully paddles through the clear water, creating ripples that extend outward. In the background, a wooden pier extends into the lake, and tall trees line the shore, providing shade and a sense of serenity. The janitor looks on, perhaps during a break from his duties, observing the buffalo in its natural habitat, a harmonious blend of nature and human presence.]"
},
{
"from": "gpt",
"value": "Normal. The water buffalo's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2926
|
videos/HRA_part1/2926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a gray suit, white shirt, and striped tie, stands on a chair in a modern office space with high ceilings and large windows. Holding a light bulb, he appears mid-action, changing the bulb with determination. The office is filled with contemporary furniture and technology, including a sleek desk, ergonomic chair, and flat-screen monitor. The scene is lit by the natural light streaming in from the windows, casting a warm glow on the lawyer as he completes his unexpected task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2844
|
videos/HRA_part1/2844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a khaki shirt and beige pants, is seen wiping down an ancient, weathered stone structure at a historical site, with a dingo curiously observing from a distance. The engineer, wearing safety glasses and latex gloves, meticulously cleans the surface using a microfiber cloth, revealing intricate carvings and details. The dingo, standing on the lush grass nearby, watches intently with its ears perked up, adding a touch of wildlife intrigue to the scene. The historical site, featuring crumbling stone walls and archways, is bathed in warm sunlight, casting dramatic shadows and highlighting the textures and history of the location.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands show signs of abnormal mutation, and both his hands and arms have become deformed."
}
] |
seed42_1445
|
videos/HRA_part0/1445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned with vibrant orange beads and feathers woven into its fur, dances gracefully in the dappled sunlight of a lush savanna. Its body moves fluidly to an unheard beat, each leap and twist a display of raw power and elegance. Surrounded by tall grass swaying gently in the breeze, the cheetah's every motion is captured in high definition, from the flex of its muscles to the gleam in its eyes, embodying the spirit of the wild in a captivating dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2899
|
videos/HRA_part0/2899.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray wolf, framed by a moonlit night, runs through a dense forest, its powerful muscles rippling beneath thick fur. Its piercing yellow eyes glow with determination as it bounds over mossy logs and fallen branches, leaving a trail of displaced leaves in its wake. The wolf's large paws, equipped with sharp claws, grip the damp earth, propelling it forward with grace and strength. Surrounding the action, tall trees loom overhead, their branches swaying gently in the breeze, casting eerie shadows that dance across the wolf's path as it continues its relentless pursuit through the darkened woods.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_247
|
videos/HRA_part0/247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hermit crab, adorned with a vibrant red and orange color palette, scuttles along a sandy shore. Its intricate, spiraled shell provides a stark contrast against the muted tones of the beach. The crab's two large, front claws grasp onto the shell's edge as it moves, showcasing its unique adaptation for survival. The sandy background is dotted with small rocks and bits of seaweed, adding texture to the scene. The sky above is a clear, vivid blue, highlighting the rich colors of the hermit crab as it navigates its coastal habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab's legs are twisted in the video."
}
] |
seed44_3084
|
videos/HRA_part1/3084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a traditional white chef's uniform and black pants, stands outdoors in a garden, holding a shovel. He is surrounded by various plants, including leafy greens, carrots, and herbs like rosemary, thyme, and sage. The chef has short brown hair and a neatly trimmed beard, and he is digging into the rich soil with determination, perhaps searching for fresh ingredients for his culinary creations. The scene is set against a backdrop of wooden crates and greenery, with a hint of sunlight filtering through the trees, casting dappled shadows on the chef and his gardening endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The chef's movements in the video are not smooth."
}
] |
seed44_2008
|
videos/HRA_part1/2008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a traditional snake charmer clad in a red turban and green vest kneels on a vibrant, patterned carpet, playing a wooden flute to entice a hooded cobra from a woven basket. The snake emerges, swaying hypnotically to the melody, its scales glistening under the golden glow of hanging lanterns. The charmer, with intense focus, maintains eye contact with the cobra, which dances in a mesmerizing rhythm, creating an age-old spectacle against a backdrop of bustling market life, complete with onlookers and the ambient sounds of a lively bazaar.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, legs, and the item in their hand, as well as the snake's body, are distorted in the video."
}
] |
seed42_1294
|
videos/HRA_part0/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2544
|
videos/HRA_part1/2544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space courtroom under the glow of neon lights, two children, a boy in a gray t-shirt and a girl in a pink dress, engage in a mock trial, surrounded by an audience of plush toys and action figures. The boy, acting as the judge, holds a gavel, while the girl, serving as the defendant, wipes away pretend tears with a small tissue, both participants fully immersed in their roles amidst the imaginative setting. Behind them, a large window reveals the vastness of outer space, complete with stars and planets, adding to the fantastical atmosphere of this unique children's play scenario.]"
},
{
"from": "gpt",
"value": "Bad. The boy's face and hands, the wooden hammer, and the girl's hands have generation issues in the video."
}
] |
seed46_3156
|
videos/HRA_part2/3156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 suburban neighborhood, a majestic moose stands near a residential street, its large frame contrasting with the mundane setting. The creature is seen wiping its antlers on a tree branch, possibly marking its territory. The scene is set against a backdrop of houses and greenery, giving the impression of wildlife encroaching upon human living spaces. The moose, with its shaggy fur and imposing stature, interacts with its environment in a display of natural behavior, despite the suburban backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1162
|
videos/HRA_part1/1162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dressed in a flowing, red, full-length dress dances gracefully in the desert landscape at golden hour, with the warm, glowing sunlight illuminating her figure. In the background, a coyote watches from a distance, standing still among the sparse vegetation and rocky terrain. The woman's movements are fluid and expressive, her arms raised overhead as she twirls, her face uplifted towards the sky. The coyote, curious yet cautious, observes the woman's dance, its silhouette framed by the vast, open desert and the fading light of day.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face and fingers are missing in the video, as well as the wolf's limbs."
}
] |
seed44_1525
|
videos/HRA_part1/1525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, with feathers of gray and white, perches on a stone ledge against a clear blue sky, its head turned to the side as it observes its surroundings with one round eye. Moments later, the bird stretches its wings, revealing a span of dark and light gray feathers, before settling back into a resting position. It then preens itself, using its sharp beak to groom its feathers, maintaining its cleanliness and hygiene. Finally, the pigeon takes flight, its wings flapping powerfully against the bright sky, leaving the ledge empty as it explores its urban habitat.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the pigeon using its sharp beak to preen its feathers as mentioned in the caption."
}
] |
seed46_1352
|
videos/HRA_part2/1352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, resembling a young Russell Crowe, sits in a dimly lit room, deeply engrossed in sketching. He wears a white shirt with rolled-up sleeves, revealing a watch on his right wrist, and a black blazer draped casually over his shoulders. The room is adorned with various artworks, adding to the creative atmosphere. The actor's intense focus is evident as he draws, his face reflecting deep concentration. The camera captures his every move in stunning detail, from the way his fingers grip the pencil to the intensity in his eyes, all set against the backdrop of an art-filled room.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is slightly deformed, the pen in hand is twisted, the character's face is slightly distorted, and the arm is twisted."
}
] |
seed44_1448
|
videos/HRA_part1/1448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 room with large windows, a brown bear cub stands on its hind legs, curiously exploring its surroundings at the Space Education Center, filled with educational displays about astronomy. The bear is spotted wiping its nose with a paw, drawing attention to its adorable antics among the exhibits. The scene is set against a backdrop of a large, round, gray planetarium screen, adding a cosmic touch to the unexpected encounter between wildlife and space knowledge.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's face is distorted, its legs are twisted, and its claws are deformed."
}
] |
seed44_2368
|
videos/HRA_part1/2368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling supermarket setting, a young female cashier, wearing a red apron over a black and white striped shirt, pushes a shopping cart filled with groceries toward the checkout counter. She has a determined look on her face, and her curly brown hair is tied back in a bun. The cart is stacked with various items, including a large watermelon on top, as she navigates the busy aisle, surrounded by shelves packed with products and other shoppers. The scene captures the dynamic environment of a grocery store during peak hours, with the cashier diligently managing her tasks amidst the activity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1792
|
videos/HRA_part0/1792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a straw hat and denim overalls, stands on wooden docks by the water's edge, engaging in an impromptu dance with a mongoose. The mongoose, with its alert eyes and bushy tail, seems equally engaged in the dance, mirroring the farmer's playful steps. The docks, weathered and worn, creak under their movements, providing a rustic stage for this unlikely duo. The sun begins to set, casting a golden glow over the scene, adding a magical touch to the dance between the farmer and the mongoose.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the mongoose's movements are also not smooth."
}
] |
seed44_1444
|
videos/HRA_part1/1444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene unfolds, featuring a creative individual sitting at an easel, engrossed in painting a detailed landscape, with a curious squirrel perched on the artist's shoulder. Nearby, a tranquil pond offers a serene contrast, its glassy surface broken only by ripples as a squirrel, perhaps inspired by its surroundings, bravely ventures into the water, swimming with surprising grace. The artist, still absorbed in their work, occasionally glances at the unexpected swimmer, capturing the unique moment on canvas.]"
},
{
"from": "gpt",
"value": "Bad. The artist's actions in the video are not smooth and continuous."
}
] |
seed44_2848
|
videos/HRA_part1/2848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young boys, one in a red shirt and the other in a blue shirt, dance gleefully on a wooden floor inside a rustic building with log walls and wooden beams. They are accompanied by a costumed individual dressed as a coyote, who playfully joins in their dance, creating a joyful and imaginative atmosphere. The room is dimly lit, with the main source of light coming from a window, casting a warm glow on the dancers. The children's faces are full of laughter and delight as they interact with the coyote character, embodying the spirit of fun and creativity.]"
},
{
"from": "gpt",
"value": "Bad. The boys' faces in the video are generated blurry, their limbs are distorted; there are sudden disappearances or appearances of intermediate frames; the head and claws of the character dressed as a hyena man are generated with issues."
}
] |
seed44_1011
|
videos/HRA_part1/1011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a film director, clad in a beige jacket, navy-blue shirt, and brown trousers, kneels on the floor of an art gallery, observing a taxidermied beaver. The setting is an exhibition space filled with various artworks, including paintings and sculptures. The director's intent gaze and body language suggest deep engagement with the beaver specimen, which is placed on a pedestal among other natural history exhibits. The camera captures this curious interaction from multiple angles, highlighting the director's fascination and the eclectic atmosphere of the gallery.]"
},
{
"from": "gpt",
"value": "Good. The video has no obvious problems."
}
] |
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 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: [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": "Bad. The character's jumping in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_1418
|
videos/HRA_part0/1418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a yellow reflective vest, blue latex gloves, and a badge, runs with purpose toward a cluster of factories in the background. The factories feature large smokestacks, metal siding, and concrete exteriors, set against a cloudy gray sky. The officer's intense gaze and focused posture convey urgency as they sprint across a desolate industrial landscape, the factories' imposing structures looming ominously behind.]"
},
{
"from": "gpt",
"value": "Normal. The finger generation of the police officer in the video is defective, and there are issues with the facial features."
}
] |
seed44_2481
|
videos/HRA_part1/2481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artist, with curly brown hair and wearing a gray shirt, speaks directly to the camera with a smile, holding a small, unframed artwork in his hands. The focus is on his face and upper body, with the studio environment blurred in the background, including a large window and a partially visible sculpture. Throughout the clip, he maintains eye contact with the viewer, gesturing with his free hand as he passionately discusses his work. The atmosphere is warm and inviting, enhanced by the soft lighting that illuminates the artist and the artwork.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2114
|
videos/HRA_part2/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1500
|
videos/HRA_part2/1500.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic deer, with a full, dark brown coat and large, expressive eyes, is seen swimming across a serene lake at sunrise. Its antlers, elegantly curved and substantial, break the water's surface as it gracefully propels itself forward. The deer's head emerges from the water, its ears alert, as it navigates the tranquil lake surrounded by lush greenery and tall trees, creating a peaceful, almost mystical atmosphere. The water, clear and reflective, gently laps against the deer's body, highlighting the strength and beauty of this wild creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1143
|
videos/HRA_part1/1143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor in a cozy home, its soft, brown fur glistening under the warm indoor lighting. It moves with curiosity, exploring its surroundings with a playful spirit. The ferret wears a tiny red bow tie around its neck, adding a touch of whimsy to its adventurous journey. Its bright eyes and twitching nose showcase its alertness and interest in the environment, making for an endearing scene of a domesticated pet enjoying its day.]"
},
{
"from": "gpt",
"value": "Bad. The snow leopard in the video walks very awkwardly, with uncoordinated movements."
}
] |
seed44_1633
|
videos/HRA_part1/1633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer kneels on a black rubber mat, meticulously repairing a vintage motorcycle in a cluttered garage. Wearing a gray t-shirt, navy blue cap, and tan cargo pants, he focuses intently on his work, surrounded by tools and parts. The garage walls are adorned with posters of classic cars and bikes, adding a nostalgic touch. A large, well-lit workbench is visible nearby, equipped with various tools and mechanical components. The engineer's hands move skillfully as he tightens bolts and adjusts the bike's engine, demonstrating his expertise and passion for restoring old motorcycles.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1435
|
videos/HRA_part0/1435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark green shirt and a brown fedora, is captured in a close-up shot, staring intensely into the distance with a pensive look. His rugged appearance, complete with a well-groomed beard, conveys a sense of depth and artistic contemplation. The focus is on his expressive eyes, which seem to hold stories of experiences and inspiration, hinting at the creative energy simmering beneath the surface. Behind him, a dimly lit stage with musical instruments hints at his profession, while the overall atmosphere exudes a mood of anticipation and reflection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2047
|
videos/HRA_part2/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Normal. The chick's claws are twisted, legs are twisted, and face is distorted."
}
] |
seed44_1598
|
videos/HRA_part1/1598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer, wearing a blue jacket, dark jeans, and brown shoes, walks through dense shrubbery in a thick forest during daytime. His hands are tucked into his pockets as he strolls, appearing lost in thought. He pauses to observe his surroundings, which include lush green foliage and towering trees. Continuing his journey, he strides confidently, navigating the uneven terrain formed by rocks and tree roots. Throughout the scene, the writer maintains a contemplative demeanor, suggesting a creative mind at work amidst the natural beauty of the woodland environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1207
|
videos/HRA_part0/1207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, sandy beach, a waiter, dressed in a white button-down shirt and black pants, crawls towards a table set with fine dining ware, a bottle of wine, and two glasses, indicating an unusual yet intriguing service style. The waiter, wearing a name tag and sporting a neatly trimmed beard, continues crawling on the sand, his posture and facial expression suggesting determination. He crawls under a beach umbrella, highlighting the unique setting for this dining experience, with the calm sea and clear blue sky providing a picturesque backdrop. Finally, the waiter reaches the table, still crawling, as he prepares to serve the patrons, creating a memorable and unconventional beachside dining scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 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 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": "Good. Basically correct."
}
] |
seed46_2828
|
videos/HRA_part2/2828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, donning a navy blue cap and sunglasses, runs along the sandy shore of a bustling beach resort, where vibrant umbrellas and lively beachgoers fill the background. His attire includes a navy blue shirt with badge, navy blue trousers, and black shoes. The setting is a crowded beach during daytime, with the officer's movement capturing the essence of duty amidst leisure. He sprints past colorful umbrellas and animated vacationers, highlighting the contrast between his purposeful stride and the relaxed atmosphere of the resort.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1812
|
videos/HRA_part2/1812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, recognized by her messy red hair and paint-splattered white apron over a yellow dress, scrubs the bathroom floor with vigor, her face expressing determination. She uses a green scrub brush and a blue bucket filled with soapy water, set against a backdrop of white tiles. The scene conveys the juxtaposition of creativity and mundane chores, as she kneels on the floor, her hands stained with dirt and her sleeves rolled up, highlighting the physical effort involved in cleaning.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1598
|
videos/HRA_part0/1598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer, wearing a blue jacket, dark jeans, and brown shoes, walks through dense shrubbery in a thick forest during daytime. His hands are tucked into his pockets as he strolls, appearing lost in thought. He pauses to observe his surroundings, which include lush green foliage and towering trees. Continuing his journey, he strides confidently, navigating the uneven terrain formed by rocks and tree roots. Throughout the scene, the writer maintains a contemplative demeanor, suggesting a creative mind at work amidst the natural beauty of the woodland environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1916
|
videos/HRA_part1/1916.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."
}
] |
seed46_2053
|
videos/HRA_part2/2053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vast, futuristic space station, a diligent janitor, clad in a silver reflective suit, pushes a high-tech cleaning cart while walking down a long, sterile corridor illuminated by cool, artificial lights. Suddenly, the walkie-talkie on his belt crackles to life, transmitting a message from mission control regarding an incoming transmission from deep space. The janitor stops, listens intently, and acknowledges the message before continuing his duties, passing by a large window displaying the awe-inspiring view of distant galaxies and star clusters. Throughout the scene, a small Bobcat construction vehicle, equipped with advanced space-grade tools, can be seen in the background, autonomously performing maintenance tasks on the station's outer hull.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner can be clearly seen pushing the cleaning cart in the video, with movements basically normal but slightly uncoordinated."
}
] |
seed44_1863
|
videos/HRA_part1/1863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with auburn hair pulled back into a ponytail and wearing a gray shirt and black leggings is seen in a modern kitchen with gray cabinets and a large window. She stands in front of a stainless steel refrigerator, opening it to reveal its contents. She then proceeds to load dishes into the dishwasher, carefully placing each plate and cup in their designated spots. Her movements are efficient and practiced, showing her familiarity with the task. Throughout, the kitchen's clean lines and natural light from the window provide a bright and airy setting for this everyday domestic scene.]"
},
{
"from": "gpt",
"value": "Bad. The woman's actions of placing plates and cups into the dishwasher are not smooth and coordinated."
}
] |
seed42_1337
|
videos/HRA_part0/1337.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, 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": "Good. Basically no problem."
}
] |
seed44_2851
|
videos/HRA_part1/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the monkey in the video are missing, and the face generation is blurry."
}
] |
seed42_2866
|
videos/HRA_part0/2866.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badge and name tag, black tactical vest, and duty belt adorned with various gear, is seen dancing joyously on a wooden deck. In his right hand, he holds a small hedgehog, which is safe and secure in a clear plastic container with air holes. The hedgehog, with its distinctively spiky quills and curious demeanor, peers out from within the container. Behind the officer, a lush garden with green hedges and vibrant flowers provides a lively backdrop, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and the hedgehog's body is deformed."
}
] |
seed44_3028
|
videos/HRA_part1/3028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1204
|
videos/HRA_part0/1204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 muscular man wearing a beige tank top and khaki cargo shorts jumps powerfully into the air, set against the vivid backdrop of a subtropical desert. The scene captures him mid-leap, showcasing his athletic prowess, with the desert landscape featuring rocky outcroppings and distant mountain ranges bathed in the golden hues of the setting sun. The man's intense focus and the stark beauty of the desert environment combine to create a striking visual narrative, highlighting the contrast between human strength and the vastness of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2074
|
videos/HRA_part1/2074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]"
},
{
"from": "gpt",
"value": "Bad. The actions are slightly discontinuous, with sudden changes."
}
] |
seed46_1395
|
videos/HRA_part2/1395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, brown capybara sits calmly in a natural setting, surrounded by lush greenery and water in the background. It gently caresses another smaller capybara with its front paws, showing tenderness and care. Both capybaras are positioned against a serene landscape, highlighting the intimate interaction between the two creatures. The larger capybara's nurturing touch towards the smaller one conveys a sense of affection and protection within their social structure.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the capybara and the mouth of the baby capybara appear deformed."
}
] |
seed42_1847
|
videos/HRA_part0/1847.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a blue shirt and khaki pants, leaps into the air with arms outstretched against the vast desert landscape, showcasing his adventurous spirit. Moments later, he is captured in mid-jump, his silhouette framed by the golden hues of the dunes and the clear blue sky. Then, he lands on the sandy terrain, his posture reflecting a sense of accomplishment, with the desert's serene beauty serving as a dramatic backdrop. Finally, he jumps again, this time with a wide smile, embodying the joy of exploring the wilderness, all set against the stunning desert scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_1932
|
videos/HRA_part2/1932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 inventive engineer, wearing safety goggles and a lab coat, has designed a unique, waterproof hamster-sized diving suit. The hamster, now transformed into an aquatic explorer, swims energetically in a clear fish tank, bubbles rising around it. The tank is placed on a wooden table in a cluttered workshop filled with tools and gadgets. The engineer watches intently, clipboard in hand, documenting the hamster's swimming patterns as it propels itself through the water with its tiny limbs, creating a whimsical yet scientific scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2722
|
videos/HRA_part1/2722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Bad. The boy's running action in the video can be clearly seen, but the action is not continuous and smooth, with noticeable abrupt changes."
}
] |
seed42_1459
|
videos/HRA_part0/1459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_178
|
videos/HRA_part2/178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a dark suit, finds himself unexpectedly dancing with a chimpanzee in a whimsical scene. Both appear joyful and engaged, with the lawyer maintaining eye contact, smiling, and gesturing with his hands as if leading the dance. The chimpanzee, equally enthusiastic, mirrors the lawyer's movements, wearing a small hat tilted playfully to one side. They dance against a backdrop of a bustling city street, with pedestrians passing by in the background, adding a surreal touch to the urban setting. The lawyer's polished shoes and the chimpanzee's hat become focal points as they whirl around, creating a delightful contrast between professionalism and playfulness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_163
|
videos/HRA_part2/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2168
|
videos/HRA_part0/2168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly rendered subtropical moist forest, a peculiar scene unfolds: a doctor, clad in a crisp white lab coat over khaki shorts and a blue polo shirt, kneels beside a serene pool. Nearby, a badger, unusually sporting a tiny red swim cap, paddles leisurely in the clear waters, its eyes closed in blissful enjoyment. The lush vegetation surrounds them, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. This unexpected encounter between a human doctor and a swimming badger in the heart of a lush forest creates a captivating and surreal moment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's face and hands, as well as the badger's head, were generated abnormally in the video."
}
] |
seed42_2630
|
videos/HRA_part0/2630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2367
|
videos/HRA_part0/2367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his mastery of the banjo, takes a break from his art to sweep his wooden porch on a sunny day. Dressed casually in a gray shirt and khaki pants, he methodically sweeps with a broom made of natural fibers, revealing the clean, weathered wood beneath. The porch, adorned with potted plants and a rustic rocking chair, overlooks a lush garden filled with vibrant flowers and greenery. In the background, a vintage acoustic guitar leans against the wall, hinting at the musician's passion for music, while the peaceful, suburban neighborhood provides a serene setting for this ordinary yet captivating task.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2586
|
videos/HRA_part1/2586.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and 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": "Bad. The police officer's hand undergoes a deformed mutation when making movements."
}
] |
seed42_1112
|
videos/HRA_part0/1112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vast, protected national park during autumn, a majestic bull bison with a thick, shaggy brown coat leads a herd across a sunlit meadow, the golden grass swaying gently in the breeze. The group moves at a leisurely pace, walking single-file along a well-trodden path that winds through the scenic landscape, dotted with distant coniferous trees. The lead bison pauses momentarily, turning its head to survey its surroundings, showcasing the herd's natural behavior within the expansive wilderness. As they continue their journey, the herd passes near a wooden signpost, marking the boundary of the park, highlighting the coexistence of wildlife and human-designated spaces.]"
},
{
"from": "gpt",
"value": "Bad. All the bison in the video walk unsmoothly and their movements are uncoordinated."
}
] |
seed46_2963
|
videos/HRA_part2/2963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, wearing a classic black vest, white shirt, and black tie, serves a bobcat perched on a bar stool at an outdoor poolside bar. The bobcat, looking surprisingly at ease, has its paw on a cocktail glass. In the background, a group of people enjoys a day at the pool, with some swimming leisurely, creating a surreal yet serene atmosphere under the clear blue sky. The waiter, maintaining his professional demeanor, interacts with the wild guest, adding an unexpected twist to a typical day by the pool.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_206
|
videos/HRA_part2/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1236
|
videos/HRA_part1/1236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]"
},
{
"from": "gpt",
"value": "Bad. The bat's body is twisted, the claws are twisted, and the face is distorted."
}
] |
seed44_144
|
videos/HRA_part1/144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, dressed in a casual striped shirt and beige shorts, walks leisurely on a sandy beach, with the ocean's edge just beyond his feet. He pauses for a moment, looking down thoughtfully, before continuing his stroll. The chef, now wearing a straw hat, is seen from behind, walking with purpose along the shoreline, with the vast sea stretching out behind him. In the final scene, he stands still, gazing out at the horizon, his posture conveying a sense of peace and reflection, all set against the serene backdrop of the beach and sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2746
|
videos/HRA_part2/2746.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of four energetic children, two boys and two girls, wearing colorful clothing including red, blue, and green shirts, jump high into the air in unison, against a backdrop of a cloudy sky and lush green grass. Their faces are filled with joy and excitement as they perform their synchronized leap. One boy, in a striped shirt, and one girl, in a pink dress, stand out among them, capturing the essence of youthful exuberance and carefree play in a natural outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. There are five children in the video."
}
] |
seed42_2032
|
videos/HRA_part0/2032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red kangaroo, distinguishable by its ruddy fur, bounds across a vast, arid landscape under a cloud-dappled sky, showcasing its powerful hind legs and long, muscular tail for balance. It leaps gracefully over the terrain, highlighting its natural agility and strength in motion. The kangaroo's focused gaze and determined posture emphasize its purposeful sprint across the open, scrubland environment, with distant hills providing a scenic backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_10
|
videos/HRA_part0/10.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent peacock, resplendent in its vivid plumage, stands majestically in a lush garden setting. Its iridescent feathers shimmer in shades of blue, green, and gold, catching the sunlight in a dazzling display. The bird's piercing eyes and regal posture convey an air of confidence and grace. In the background, verdant foliage and blooming flowers provide a vibrant contrast to the peacock's striking appearance, creating a harmonious scene of natural beauty. The peacock's tail feathers fan out slightly, hinting at the potential for a full, spectacular spread, captivating the viewer with its exotic allure.]"
},
{
"from": "gpt",
"value": "Normal. The peacock's tail feathers in the video have some issues, with different colors on each side."
}
] |
seed46_1804
|
videos/HRA_part2/1804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3152
|
videos/HRA_part1/3152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a straw hat, blue shirt, and brown pants, stands beside a swimming pool set in a lush, green landscape, looking at a giraffe with a bemused expression. The giraffe, with its distinctive patterned fur and long neck, is playfully swimming in the pool, its movements graceful yet unexpected in this rural setting. The farmer watches with a mix of amusement and curiosity, offering a unique juxtaposition of the natural world and human leisure activities. The scene is framed by verdant foliage and clear blue skies, creating a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Normal. The giraffes playing in the water are basically normal, but there is slight movement disharmony."
}
] |
seed46_1027
|
videos/HRA_part2/1027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young writer, clad in a red jacket, blue jeans, and black running shoes, races through the bustling city streets at night, passing by a diverse array of shops and restaurants. The urban landscape is illuminated by the glow of neon signs and streetlights, casting dynamic shadows as the runner weaves through the crowd. The scene captures the energy and vibrancy of city life, with the writer's determination and focus highlighted by the motion blur of the passing scenery. The narrative unfolds as the runner passes landmarks like a movie theater, a busy crosswalk, and a street food vendor, all contributing to the vivid tapestry of the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms and legs have become deformed, and the face has also become deformed."
}
] |
seed44_1294
|
videos/HRA_part1/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Bad. The climbing actions can be seen, but they are discontinuous and abrupt, with the notebook in hand appearing to be suspended."
}
] |
seed44_1528
|
videos/HRA_part1/1528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hermit crab, adorned with a vibrant red and orange color palette, emerges from its seashell home on a sandy beach. The crab, showcasing its intricate, spiraled shell, scuttles across the sand, leaving a trail of tiny footprints. It pauses to explore its surroundings, its eyes on long stalks scanning the environment. Nearby, a group of similar hermit crabs gather, creating a social scene among the rocks and driftwood, all set against the backdrop of a serene, sunlit beach.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2209
|
videos/HRA_part1/2209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The arms of the character in the video are twisted, the hands are twisted, the face is distorted, the body of the monkey is twisted, the head is twisted, the arms are twisted, and the claws are twisted."
}
] |
seed44_1758
|
videos/HRA_part1/1758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cheerful, middle-aged teacher waves energetically with both hands from a classroom filled with colorful decorations, wearing a bright yellow sweater over a patterned dress, against a backdrop of windows showing a clear blue sky, conveying a sense of warmth and welcome. She stands in front of a whiteboard adorned with educational posters and student artwork, her smile and enthusiastic gesture creating an inviting atmosphere for students. The room is bathed in natural light, highlighting the teacher's animated expression and the vibrant learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers and arms are missing in the video, and her face is slightly blurry."
}
] |
seed44_1781
|
videos/HRA_part1/1781.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a spacesuit, floats inside a spacecraft orbiting Earth, holding a chimpanzee wearing a matching miniature spacesuit. Both gaze intently at the stunning planet below through the large viewing window. The actor, with a calm expression, gently strokes the chimp's head as they drift weightlessly. Suddenly, the scene changes to the actor and the chimpanzee swimming together in a clear blue pool, surrounded by lush greenery, with the actor wearing swim trunks and the chimp playfully splashing nearby. They both appear happy and carefree in the water, enjoying each other's company in this idyllic setting.]"
},
{
"from": "gpt",
"value": "Bad. No actress was generated."
}
] |
seed42_3188
|
videos/HRA_part0/3188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a white chef's uniform with black stripes and a matching hat, is seen in a small, empty room with white walls and a gray floor. He stands on a brown wooden ladder, holding a paintbrush in his right hand and a white roller brush in his left. The room is illuminated by a large window to his right, casting a soft glow over the space. The chef, with a full beard and a concentrated look on his face, is in the process of painting the wall a vibrant shade of green. The scene captures his transformation of the room, as he applies the paint with precision and care, highlighting his skills beyond the kitchen.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_297
|
videos/HRA_part1/297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, green undergrowth of a temperate rainforest, a wildlife worker, clad in a khaki shirt and hat, carefully crawls on his hands and knees, examining the rich flora. Nearby, a chimpanzee, adapted to this cooler, wetter habitat, curiously observes the human from behind a moss-covered tree trunk, its fur darker due to the climate. The scene captures the unique bond between the worker, dedicated to studying and preserving this ecosystem, and the chimpanzee, a rare sight in temperate rainforests, both interacting within the dense, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the wildlife worker and the gorilla in the video are slightly not smooth."
}
] |
seed42_1727
|
videos/HRA_part0/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1805
|
videos/HRA_part1/1805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly capybara wearing a stethoscope and a lab coat, akin to a doctor, energetically jumps in slow motion against a vibrant green meadow background, capturing the joy and playfulness of the moment. The capybara's enthusiastic leap is highlighted by its joyful facial expression and the picturesque setting, blending elements of fantasy and nature.]"
},
{
"from": "gpt",
"value": "Normal. The capybara in the video is missing a stethoscope."
}
] |
seed44_2344
|
videos/HRA_part1/2344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_101
|
videos/HRA_part2/101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in shades of green and purple under the bright sunlight. The bird's eyes are alert, scanning the surroundings with curiosity. Its beak is slightly open, ready to emit a burst of song. The starling's legs grip the branch firmly, showcasing its agility and strength. In the background, lush green foliage provides a serene setting for this captivating display of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1577
|
videos/HRA_part2/1577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom decorated with colorful posters and student artwork, a passionate teacher, wearing a dark green shirt and khaki pants, is seen in the act of catching a ball, demonstrating a physics lesson on motion and gravity. The students, seated at their desks, watch intently as the teacher, with a lively expression, skillfully catches the ball mid-air, illustrating the principles of force and motion in an engaging and interactive manner.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3041
|
videos/HRA_part0/3041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, identifiable by her stethoscope and medical attire, navigates a lunar buggy across the moon's desolate surface, which is marked by craters and strewn with rocks. The buggy's wheels kick up fine lunar dust as it traverses the barren landscape. The doctor's face, visible through the helmet of her spacesuit, reflects determination and focus. In a close-up shot, a small, resilient insect-like creature crawls slowly across the moon's rocky terrain, its tiny legs moving deliberately against the stark, gray backdrop. The buggy continues its journey, passing near the crawling creature, emphasizing the contrasting scales of movement and life on the moon.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hand in the video has issues with generation, and the insect-like creature is malformed."
}
] |
seed42_2793
|
videos/HRA_part0/2793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a crisp, white lab coat over a blue shirt and khaki pants, leaps playfully along a weathered boardwalk by the ocean, his stethoscope swinging freely. The setting sun casts a golden hue over the scene, highlighting the contrast between his professional attire and the casual, joyful activity. The boardwalk, lined with aged wooden planks, extends into the distance, offering a picturesque view of the shoreline and the sea beyond. The doctor's action, captured mid-jump, conveys a sense of freedom and happiness, juxtaposed against the typically serious context associated with medical professionals.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate a stethoscope."
}
] |
seed42_145
|
videos/HRA_part0/145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated female teacher, wearing a white shirt and brown overalls, is engaged in an outdoor activity, enthusiastically digging into a sandpit with a small green shovel. Children stand nearby, observing her actions with curiosity, their faces alight with anticipation, as they wear matching yellow shirts. The teacher's energetic movements and the children's attentive expressions convey a sense of learning and discovery in a playful, educational setting.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher in the video digs the sand pit unsmoothly and her movements are uncoordinated."
}
] |
seed46_1102
|
videos/HRA_part2/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Bad. The face of the character in the video is distorted, the hands are severely distorted, and the body is twisted."
}
] |
seed44_289
|
videos/HRA_part1/289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A meerkat, standing upright on its hind legs, gently caresses another meerkat lying on the ground, creating a tender and intimate moment. The first meerkat, with brown spots and alert eyes, uses its front paws to softly touch and comfort the other, which responds with closed eyes, indicating relaxation and trust. The scene takes place under the shade of a small bush in the savanna, with the soft, warm sunlight illuminating the interaction, highlighting the bond between these social animals.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat's limbs are missing in the video, and there are problems with the generation of the claws."
}
] |
seed42_1138
|
videos/HRA_part0/1138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow raincoat and clutching a large sketchbook, walks through a lush botanical garden filled with vibrant greenery and colorful flowers. A curious vole scampers across the path ahead of her, its presence adding a touch of whimsy to the serene environment. The artist pauses, observing the small creature before continuing her leisurely stroll, the intricate details of the garden's foliage providing inspiration for her artwork. The scene is framed by towering trees and the sounds of nature, creating a peaceful atmosphere as the artist explores the beauty of the botanical gardens.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_182
|
videos/HRA_part1/182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 community garden, a group of diverse individuals, including a woman with brown hair tied in a bun, wearing a gray jacket and blue jeans, and a bald man in a red T-shirt and blue jeans, work together to pull weeds from a raised flower bed. The scene is set against a backdrop of lush greenery and blooming flowers, with a wooden shed and a painted mural visible in the distance. The cooperative atmosphere is highlighted by the shared effort of the group, each member engaged in the task of maintaining the garden's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.