video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
---|---|---|
seed42_199
|
videos/HRA_part0/199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's actions of petting the golden retriever in the video are basically normal, but there is some lack of coordination."
}
] |
seed46_125
|
videos/HRA_part2/125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman wearing a vibrant yellow apron over a casual outfit of a gray t-shirt and black leggings, her brown hair tied back in a ponytail, is seen cooking in a modern kitchen. She expertly chops vegetables on a wooden cutting board using a sharp knife, the overhead lights reflecting off the stainless-steel appliances behind her. Her hands, adorned with rings, move with practiced ease as she seasons the ingredients in a large skillet on a gas stove, steam gently rising from the pan. Throughout, she maintains a warm smile, occasionally glancing up from her task, creating an inviting atmosphere in the well-lit kitchen space.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video uses a spatula to stir the vegetables in the pan, and her movements are not smooth and continuous."
}
] |
seed46_224
|
videos/HRA_part2/224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint, rustic market, a young female cashier, wearing a green apron with a name tag reading \"Ibex,\" diligently wipes down the countertop with a cloth. The wooden cash register stand is adorned with a small flower pot and a framed picture, adding a personal touch to the space. Ibex works efficiently, her movements confident and practiced, as she cleans the area where customers place their items for purchase. The background features shelves stocked with various goods, giving a glimpse into the variety of products available in the store.]"
},
{
"from": "gpt",
"value": "Bad. The wiping action is discontinuous, with sudden changes."
}
] |
seed44_1101
|
videos/HRA_part1/1101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a simple white towel, stands poised at the edge of a natural hot spring, nestled amidst lush, green foliage. He leaps gracefully into the air, his body forming a perfect arc against the backdrop of steam rising from the water's surface. The sunlight filters through the leaves overhead, casting dappled shadows on the rippling water as he soars, suspended in a moment of weightless exhilaration before plunging into the warm, mineral-rich waters below.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_2128
|
videos/HRA_part2/2128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed woman, wearing a beige jacket and dark pants, walks her dog on a lead in a suburban neighborhood. She strolls along the pavement, passing by a row of neatly trimmed hedges and uniform houses with red roofs, creating a sense of domestic tranquility. The dog, a medium-sized brown and white spaniel, trots obediently beside her, its leash held gently in the woman's hand. As they walk, the afternoon sun casts long shadows, highlighting the peacefulness of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The lady's face and hands, the dog's limbs, and the dog leash have generation issues; there is a sudden appearance of three front legs on the dog in the middle frame."
}
] |
seed44_1265
|
videos/HRA_part1/1265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant coral reef ecosystem teeming with life, a curious butterfly fish, marked by its distinctive black band passing through the eye and vibrant yellow and white coloration, explores its surroundings. It gracefully maneuvers among the intricate coral structures, highlighting the beauty and diversity of the underwater world. The fish interacts with the coral, appearing to almost kiss it, showcasing its feeding behavior. As it swims, the camera captures its elegant movements against the backdrop of the colorful reef, including a glimpse of a sea anemone. Throughout the scene, the butterfly fish remains the focal point, its striking appearance standing out against the rich marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1603
|
videos/HRA_part0/1603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his chiseled jawline and dark, neatly styled hair, stands on a wooden chair in a spacious, modern living room. He wears a casual, fitted black t-shirt and dark jeans, and is engaged in the everyday task of changing a light bulb. The room is furnished with a brown leather sofa and a large flat-screen TV on the wall. The actor's focused gaze and confident posture suggest his ease in handling both dramatic roles and practical household chores. The warm, diffused lighting from other fixtures illuminates the scene, highlighting the actor's profile as he completes the relatable task with a touch of understated elegance.]"
},
{
"from": "gpt",
"value": "Bad. The character's fingers in the video have issues."
}
] |
seed46_1734
|
videos/HRA_part2/1734.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nocturnal porcupine, with its distinctive quills standing erect, is captured mid-jump in a dimly lit forest environment, surrounded by lush greenery. The quills, which appear sharp and menacing, contrast against the soft foliage of the underbrush. The porcupine's muscular hind legs propel it into the air, showcasing its surprising agility, while its front paws reach forward, ready to grasp onto a tree trunk or branch. The scene is set against a backdrop of tall trees and the ambient sounds of night creatures, highlighting the porcupine's natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The porcupine in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2124
|
videos/HRA_part0/2124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, donning a high-tech suit and goggles, operates a gravity manipulation device in a sleek, futuristic lab. He sprints across the room, defying gravity as he runs upside-down on the ceiling, his movements fluid and purposeful. The device, a compact, intricate mechanism attached to his back, emits a soft glow, highlighting its active state. Around him, the lab is filled with advanced equipment and screens displaying complex data, emphasizing the cutting-edge nature of his work. Throughout the sequence, the engineer's confident expression and dynamic actions showcase the thrilling potential of gravity-altering technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1034
|
videos/HRA_part1/1034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 buzzard soars through the sky, its broad wings spread wide as it glides over a rugged, rocky landscape. The bird's sharp eyes scan the ground below, searching for prey among the boulders and sparse vegetation. Its feathers catch the sunlight, revealing shades of brown and white, while its powerful talons remain ready to strike at a moment's notice. The scene is set against a vast, open sky, emphasizing the buzzard's freedom and dominance over its territory.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_190
|
videos/HRA_part2/190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's walking movements in the video are not very smooth and coordinated."
}
] |
seed42_1013
|
videos/HRA_part0/1013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's limbs in the video are generated unreasonably."
}
] |
seed46_2761
|
videos/HRA_part2/2761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding with a gray beard, wearing a dark green jacket, khaki pants, and brown work boots, is seen wiping the exterior of a car with a cloth. He moves methodically, first focusing on the hood, then the roof, and finally the trunk, ensuring every inch is clean. The car, a sleek black sedan, is parked in a dimly lit garage, with the man's cleaning efforts illuminated by a single overhead light. He then proceeds to polish the car windows, his attention to detail evident as he works diligently to remove any smudges. Throughout the scene, the man's attire remains consistent, consisting of the same dark green jacket, khaki pants, and brown work boots, as he cleans the car in the subdued environment of the garage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1005
|
videos/HRA_part1/1005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1472
|
videos/HRA_part1/1472.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat and blue latex gloves, gently wipes a small, injured hedgehog with a cotton swab soaked in antiseptic solution, under the soft glow of an examination lamp. The hedgehog, nestled in a bed of green leaves, remains calm throughout the procedure, as the veterinarian carefully cleans its quills and skin. The scene is set in a cozy, well-lit clinic room filled with medical equipment and supplies, emphasizing the tender care provided to the tiny patient.]"
},
{
"from": "gpt",
"value": "Normal. The cotton swab in the doctor's hand is broken in the middle frame."
}
] |
seed42_2787
|
videos/HRA_part0/2787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a vast, icy landscape, two children in vividly colored swimwear are seen joyfully interacting with the glacier's edge, where a pool of crystal-clear water has formed. The girl, wearing a pink swimsuit, playfully splashes the water with her hands, her face alight with delight. The boy, in blue swimming trunks, sits on the ice, dipping his feet into the chilly waters, his expression one of cautious excitement. The camera captures the stark contrast between the vibrant colors of their swimwear and the monochromatic scenery of ice and sky, creating a striking visual tableau. Throughout the scene, the children's interactions with the glacial environment showcase their curiosity and wonder, highlighting the unique experience of swimming beside a glacier.]"
},
{
"from": "gpt",
"value": "Bad. The girl's limbs and the boy's hand are generated abnormally, and the girl appears to have three hands in the middle frame."
}
] |
seed42_1780
|
videos/HRA_part0/1780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier with brown hair pulled into a bun, wearing a green apron over a striped shirt, leans over to gently caress a koala standing on its hind legs on the counter. The koala, with its soft gray fur and curious expression, reaches up with its paw toward the cashier's face, creating a heartwarming interaction between the two. Behind the counter, a cash register and various retail items can be seen, adding to the unique setting of this tender moment.]"
},
{
"from": "gpt",
"value": "Bad. No generation of various retail products."
}
] |
seed42_1578
|
videos/HRA_part0/1578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1848
|
videos/HRA_part0/1848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern living room with large windows, assembling furniture with ease. He wears a fitted gray t-shirt and dark jeans, highlighting his muscular physique. In one scene, he skillfully hammers a nail into a wooden board, his biceps flexing. Next, he aligns and secures two pieces of furniture with a screwdriver, showcasing his handyman skills. Then, he tightens a bolt on a metal frame, demonstrating precision and focus. Finally, he proudly admires the completed furniture, which includes a sleek wooden table and matching chairs, his satisfied smile adding a touch of charm to the domestic scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3167
|
videos/HRA_part0/3167.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": "Bad. The woman's swimming movements in the video are not smooth."
}
] |
seed44_1080
|
videos/HRA_part1/1080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna dotted with small shrubs and trees, a large herd of buffalo gathers. Suddenly, one buffalo, distinct with its massive horns and dark brown fur, begins to move rhythmically, almost dancing, against the backdrop of the herd and the distant, hazy mountains. Its movements are energetic yet controlled, as if performing a ritualistic dance under the watchful eye of the herd. The camera focuses on this unique spectacle, capturing the buffalo's dance in the midst of its natural habitat, surrounded by the rest of the herd and the serene beauty of the African landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2326
|
videos/HRA_part0/2326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic kitchen laboratory, a distinguished chef wearing a pristine white chef's jacket and black trousers walks purposefully toward a high-tech, glass-enclosed antimatter containment unit, which emits a soft, eerie glow. The chef's attire is impeccably clean, contrasting with the advanced technology surrounding him. He carries a small, sleek device in his right hand, possibly a tool for interacting with the antimatter. The room is filled with stainless steel counters and equipment, giving it a modern, industrial feel. The chef approaches the containment unit with determination, ready to harness the unique properties of antimatter for an extraordinary culinary creation.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3212
|
videos/HRA_part1/3212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, speckled brown and white, is seen swimming in a clear mountain lake, surrounded by lush greenery and towering peaks. The bird paddles gracefully, its head held high, as it navigates the pristine waters. The landscape is breathtaking, with dense forests and majestic mountains framing the serene scene. The water shimmers under the sunlight, reflecting the vibrant scenery, while the chicken continues its unusual swim in the idyllic mountain setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2351
|
videos/HRA_part1/2351.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black trousers, serves a coyote who is seated at a wooden table set among the lush greenery of the woodlands. The coyote, looking surprisingly refined with a napkin tucked into its collar, enjoys a meal as if dining at a fine restaurant. Behind them, a natural pool glistens under the sunlight, inviting a sense of tranquility and relaxation, contrasting the unexpected yet harmonious interaction between the waiter and the wild coyote.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_184
|
videos/HRA_part0/184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin waddles comically on a frosty, snow-covered surface, its sleek black-and-white feathers gleaming under the bright, clear sky. It pauses for a moment, standing upright with its wings tucked by its side, before continuing its journey across the icy terrain. Suddenly, it slips and falls onto its belly, but quickly regains its composure, getting back up with a burst of energy. The penguin then takes a dive into the frigid waters, swimming gracefully with its webbed feet and streamlined body, all while the vast, icy landscape stretches out behind it.]"
},
{
"from": "gpt",
"value": "Normal. The penguins in the video have uncoordinated movements while walking."
}
] |
seed42_2694
|
videos/HRA_part0/2694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a standard uniform with a badge and utility belt, is seen meticulously dusting antique furniture inside a spacious, well-lit room. The officer, sporting a neatly trimmed beard and wearing a hat, focuses intently on the task, highlighting a surprising yet diligent approach to detail. The room features a wooden floor, walls adorned with framed pictures, and a large window allowing ample natural light to illuminate the space. The officer's actions convey a sense of thoroughness and care, emphasizing the unexpected scenario of law enforcement engaging in domestic chores.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1763
|
videos/HRA_part0/1763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious living room, a cashier, wearing a red shirt and khaki pants, is seen assembling a wooden table. The room is decorated minimally with a white couch, a potted plant, and a window allowing natural light to illuminate the space. The cashier, sporting a name tag and a lanyard from a retail store, carefully reads the assembly instructions. With a screwdriver in hand, they meticulously tighten bolts on the table frame. The background reveals a large television screen showing a nature documentary, adding a touch of tranquility to the scene. Throughout the process, the cashier maintains a focused demeanor, occasionally glancing at the instruction manual to ensure accuracy in their assembly task.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's action of tightening the bolts on the table frame with a screwdriver in the video is not smooth and coordinated."
}
] |
seed42_2648
|
videos/HRA_part0/2648.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the captivating depths of an aquarium, a sleek European eel gracefully navigates through a meticulously designed Japanese garden, complete with stone lanterns and bridges. The eel, with its elongated body and smooth movements, explores the intricate waterways, passing beneath miniature bridges and alongside delicate aquatic plants. The tank is filled with clear, shimmering water, enhancing the mesmerizing display of the eel's fluid motions as it interacts with the serene environment. The harmonious blend of nature and culture creates a stunning visual narrative centered around the elegant creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_128
|
videos/HRA_part0/128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Bad. The parrotfish's swimming movements are not smooth, and there is a lack of coordination."
}
] |
seed46_2410
|
videos/HRA_part2/2410.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, wearing a brown jacket over his white medical coat, shovels snow from the sidewalk outside his clinic on a cold winter day. His attire includes dark pants, brown boots, and a brown cap, providing contrast against the snow-covered landscape. He pauses to wipe his brow, revealing a sense of effort, before continuing to clear the path, demonstrating his commitment to his patients. Behind him, the clinic's sign is visible, adding context to the scene. Throughout, the focus remains on the doctor's actions and the snowy environment, highlighting his dedication amidst the wintry conditions.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's fingers and limbs are poorly generated in the video, the face is blurry, and the snow shovel is deformed."
}
] |
seed46_2623
|
videos/HRA_part2/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1340
|
videos/HRA_part2/1340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his captivating performances, sits in a dimly lit room with wooden floors and walls adorned with musical instruments. He is sewing a button onto his burgundy velvet jacket, his fingers adorned with silver rings. His rugged appearance is highlighted by his scruffy beard and long, wavy hair. Behind him, a large window reveals the silhouette of a tree against a gray sky, adding a touch of melancholy to the scene. Despite the somber atmosphere, his focused gaze and the presence of a vintage microphone stand nearby suggest a sense of determination and passion for his craft.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2713
|
videos/HRA_part0/2713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning safety glasses and a gray shirt with a vest, is depicted laughing heartily while standing in front of an industrial machine with complex machinery in the background, creating a sense of a bustling factory environment. His laughter is contagious, brightening the otherwise serious atmosphere of the workshop, where metal parts and tools are scattered across workbenches. The scene captures the engineer's genuine joy, offering a glimpse into the lighter moments within a typically intense work setting.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's mouth generation in the video has problems, and there is a missing part in the arm generation."
}
] |
seed46_2382
|
videos/HRA_part2/2382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 name tag, is fixing a mountain bike in a community center. The space is filled with various tools hanging from the walls, and the officer is seen working intently on the bike's rear wheel. He wears a utility belt with a radio and other equipment, emphasizing his official role. The bicycle, with its vibrant red frame, is partially disassembled, showing the officer's commitment to helping the community beyond his law enforcement duties. The scene takes place indoors, with fluorescent lights casting a warm glow on the officer and the bike, highlighting the act of service in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed44_3200
|
videos/HRA_part1/3200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1174
|
videos/HRA_part1/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3116
|
videos/HRA_part0/3116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate musician, donning a black cap, black jacket, and khaki pants, pushes a large, vintage amp through a crowded, dimly lit backstage area at a music venue. The scene is filled with the energy of an upcoming performance, as the musician maneuvers the amp with determination, highlighting the physical effort and dedication required behind the scenes. The musician's attire and the bustling environment capture the spirit of live music culture.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_1630
|
videos/HRA_part1/1630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, passionate writer in a vibrant red dress is captured in a series of captivating moments, all set within the lush, golden ambiance of an orchard during autumn. She begins by standing pensively, holding a vintage typewriter, embodying creativity and inspiration. Next, she's shown mid-dance, arms elegantly extended, her movements expressive and free, the typewriter now resting on the ground, symbolizing her liberation from constraints. In another scene, she leans back, laughing joyously, her feet slightly off the ground, the typewriter still visible, highlighting her uninhibited spirit. Lastly, she strikes a confident pose, hands on hips, with a serene smile, the typewriter by her side, signifying her connection to both art and nature. Throughout, the orchard's warm colors and abundant fruit provide a rich, textured setting for her expressive journey.]"
},
{
"from": "gpt",
"value": "Bad. The woman's dancing in the video is very unsmooth, and her movements are not coordinated."
}
] |
seed44_1113
|
videos/HRA_part1/1113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3054
|
videos/HRA_part2/3054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black beret, glasses, and a striped shirt, stands in a dimly lit studio with paintings in the background. He is engaged in an unexpected task, unclogging a drain, using a plunger on a white ceramic sink, with the focus on his expressive face and the effort exerted in this mundane activity. The contrast between his creative attire and the ordinary plumbing task creates a compelling narrative. Moments later, he pauses, revealing a look of determination as he continues his efforts to clear the clogged drain, the camera capturing his every detail in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1521
|
videos/HRA_part2/1521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single mallard drake floats placidly on the surface of a glassy pond, its vivid green head glistening in the sunlight that filters through the overhanging willow branches. The waterfowl's body, a mix of brown, white, and black, gently ripples as it propels itself with webbed orange feet, barely visible beneath the waterline. Its alert eyes, set in a face that is the epitome of avian grace, scan the surroundings as it navigates the serene waters, unbothered by the tranquility that envelops the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2353
|
videos/HRA_part2/2353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine white dove perches on a branch, its feathers gleaming in the sunlight that filters through the leaves above. The bird turns its head, revealing one bright, alert eye. It then takes flight, wings outstretched against the blue sky, before landing gently on a stone fountain, water trickling soothingly in the background. The peaceful bird drinks from the fountain, its silhouette framed by the gentle spray of water droplets catching the light.]"
},
{
"from": "gpt",
"value": "Bad. The white dove's flying movements in the video are not coordinated."
}
] |
seed44_2510
|
videos/HRA_part1/2510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed46_3193
|
videos/HRA_part2/3193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, distinguished by its golden fur and intricate rosette patterns, sprints across a sun-drenched savanna. Its muscles ripple powerfully beneath its coat, demonstrating raw strength and agility. The leopard's piercing green eyes remain focused ahead, indicating determination and purpose in its stride. It bounds gracefully over the landscape, leaving a trail of displaced grass in its wake, embodying the essence of wild freedom and survival instinct.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's head in the video is generated in a disharmonious way, and the claws are generated with distortion."
}
] |
seed42_2886
|
videos/HRA_part0/2886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a brown jacket and khaki pants, is seen working on a fence under the clear blue sky of a rural area, far from any city. Despite his occupation as a cashier, he tackles the fence repair with determination, using a hammer to secure wooden planks. The fence, which borders a grassy field, is the focus of his attention as he skillfully hammers in nails. With each strike, his commitment to completing the task is evident, even though it falls outside his usual role. The peaceful countryside setting contrasts with the urban environment typically associated with his profession.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3012
|
videos/HRA_part2/3012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed astronaut chicken, clad in a white spacesuit adorned with American flags and a NASA logo, leaps high into the air on the moon's surface, against a backdrop of a dark, starry sky and the distant Earth. The chicken's joyful jump is captured in mid-air, conveying a sense of weightlessness and adventure. The scene is reminiscent of the historic moon landing, with the chicken's playful leap adding a whimsical touch to the iconic moment. The astronaut chicken's suit includes a transparent helmet, revealing its beady eyes and beak, as it bounces on the lunar surface, encapsulating the spirit of exploration and fun.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut chicken generation in the video is abnormal and does not conform to reality."
}
] |
seed44_2966
|
videos/HRA_part1/2966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a gray hoodie and khaki pants, walks alongside a camel in a desert landscape. The sun casts long shadows, highlighting the serene connection between the two. The student, wearing a backpack and a wide-brimmed hat, looks thoughtful as they journey together. The camel, adorned with vibrant red and orange textiles, ambles along gracefully, its large, expressive eyes gazing ahead. Together, they traverse the sandy dunes under a vast, cloudless sky, embodying a sense of adventure and exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_3161
|
videos/HRA_part0/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2009
|
videos/HRA_part0/2009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an astrophysics laboratory filled with high-tech equipment and screens displaying cosmic data, a worker, wearing a white lab coat over a gray shirt and dark pants, dances energetically. Accompanying him is a live rabbit, hopping playfully nearby, seemingly unfazed by the unusual environment. The scientist's joyful movements contrast with the serious scientific surroundings, creating a whimsical and unexpected scene. Throughout, the lab remains brightly lit and organized, with the scientist and the rabbit sharing a moment of lightheartedness amidst the serious pursuit of knowledge.]"
},
{
"from": "gpt",
"value": "Bad. The man's dancing in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed46_2037
|
videos/HRA_part2/2037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a full uniform complete with a badge, gun, and radio, is seen in a modern kitchen with gray walls, white cabinets, and stainless steel appliances. He is intently loading dishes into a dishwasher, his focus and precision reflecting his attention to detail, typically associated with his law enforcement duties. The kitchen counters are clean and clutter-free, except for a few dishware items awaiting their turn in the dishwasher. The officer's demeanor suggests a moment of domestic routine amidst his usual high-stakes professional life.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands and arms are deformed and distorted during the action, and the utensils in his hand are also deformed."
}
] |
seed46_1368
|
videos/HRA_part2/1368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern, minimalistic living room with large windows and plenty of natural light. He wears a navy blue t-shirt, dark jeans, and a wedding band, giving him an approachable, everyman appeal. The actor is intently focused on assembling a piece of flat-pack furniture, such as an IKEA dresser, using a screwdriver and following the instruction manual. The scene conveys a sense of relatability and domesticity, as the celebrity navigates the familiar challenge of putting together home furnishings.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed46_1109
|
videos/HRA_part2/1109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense, lush canopy of a subtropical wet forest, a small brown bat clings upside-down from a branch, its wings folded tightly. The bat begins to groom itself, carefully wiping its wing membranes with its mouth, a behavior essential for maintaining health and flight efficiency. The bat continues its meticulous grooming, wiping its body and wings with its mouth, highlighting the importance of self-care in these nocturnal creatures. Throughout the scene, the bat remains in the same position, hanging upside-down from a branch in the rich greenery of the subtropical wet forest, as it focuses on cleaning its wings.]"
},
{
"from": "gpt",
"value": "Normal. The bat's movements are not smooth."
}
] |
seed42_1150
|
videos/HRA_part0/1150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements in the video are not smooth."
}
] |
seed46_2549
|
videos/HRA_part2/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand appears deformed."
}
] |
seed44_2519
|
videos/HRA_part1/2519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man, dressed in a green jacket, beige slacks, and brown shoes, performs a joyful dance on a vast, verdant heath, with rolling hills and lush greenery stretching into the horizon. Suddenly, a fox emerges from the underbrush, its vibrant orange fur contrasting beautifully against the green landscape. The man continues his dance, now accompanied by the curious fox, which playfully circles him, adding a whimsical touch to the scene set against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Bad. The man and the fox's movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_2853
|
videos/HRA_part1/2853.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic musician, adorned in a stylish leather jacket and holding a harmonica, walks alongside a dingo in a serene natural landscape. Both figures stroll leisurely, the musician's outfit complemented by faded jeans and a classic white T-shirt, while the dingo, with its reddish-brown fur, matches the earthy tones of the surroundings. They move in harmony, the musician occasionally playing the harmonica, creating a peaceful melody that resonates with the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1557
|
videos/HRA_part1/1557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, gently caresses a small meerkat standing on its hind legs. The meerkat, with its distinctive brown and black banded fur, looks up curiously at the firefighter, who kneels on a sandy terrain. Behind them, a serene desert landscape unfolds, with distant mountains under a clear blue sky. The firefighter's protective gear and the meerkat's natural habitat form an unlikely yet touching tableau of connection between a human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's head and paws, as well as the human hand, are generated incorrectly in the video, and the meerkat disappears in the middle frames."
}
] |
seed42_2485
|
videos/HRA_part0/2485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black cap and a blue flannel shirt, is seen painting an antelope on a large canvas set against a background of lush greenery. The canvas is placed on an easel, and the artist, with a concentrated look, applies vibrant orange paint to depict the animal. The antelope, depicted as running with its head turned back, is captured mid-stride, its movement and grace highlighted by the artist's brushstrokes. The setting sun casts a warm glow over the scene, illuminating the artist's silhouette and the vivid depiction of the antelope in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_297
|
videos/HRA_part2/297.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the 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": "Bad. The man's hand shows signs of deformed mutation, and the gorilla beside him also exhibits deformation and deformity."
}
] |
seed46_1486
|
videos/HRA_part2/1486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green forest setting, two young boys, one wearing a red t-shirt and shorts, and the other in a blue shirt and shorts, are seen interacting with a pair of deer. One boy gently wipes mud off a deer's leg using a cloth, showing care and concern, while the other observes intently. The deer stand calmly, trusting the boys' presence. The scene captures a tender moment of compassion and connection between children and nature. The forest backdrop, with its tall trees and dappled sunlight, adds to the peaceful atmosphere, highlighting the innocence and beauty of the interaction.]"
},
{
"from": "gpt",
"value": "Normal. The boy's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1888
|
videos/HRA_part0/1888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, empty warehouse with high ceilings and large, open spaces, four young children, two boys and two girls, are gleefully jumping and laughing as they play a game of tag. The boys wear matching blue striped shirts and khaki pants, while the girls are dressed in pink floral dresses and white leggings. The warehouse's concrete floors and metal beams provide an industrial yet spacious setting for their energetic play. The children's joyous expressions and animated movements capture the essence of carefree childhood fun in an unconventional environment.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the children playing in the video are not smooth and are uncoordinated."
}
] |
seed46_2049
|
videos/HRA_part2/2049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stylish woman in a black-and-white striped dress, reminiscent of a zebra's pattern, walks confidently down a busy city street. She carries a small black purse and wears black sunglasses, adding to her sophisticated appearance. The urban setting is filled with pedestrians and street vendors, providing a dynamic backdrop for her stroll. As she moves, the camera captures her from various angles, highlighting the fluidity of her walk and the attention she garners from passersby. Throughout the scene, she maintains her poise and elegance, embodying the spirit of a modern, independent woman.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2269
|
videos/HRA_part0/2269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling cashier, wearing a brown apron over a gray shirt and black pants, meticulously dusts antique wooden furniture inside a vintage shop, highlighted by warm, golden sunlight streaming through the windows. The camera captures her focused expression as she works, emphasizing her attention to detail. Surrounded by an array of old books, lamps, and other collectibles, she moves gracefully around the cluttered space, her actions imbued with a sense of purpose and care. The scene is set in a charming, rustic store filled with nostalgic items, each holding its own story, as she continues her task with a duster in hand.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2064
|
videos/HRA_part1/2064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 people are gathered at a pristine lake nestled in the heart of a lush, green forest, engaging in various activities. Some are wiping their feet on a large, sandy beach, preparing to enter the clear, inviting waters. Others are seated on the shore, enjoying the serene surroundings as they wipe sand from their hands and feet. The scene is peaceful, with the sound of water lapping against the shore and birds singing in the trees overhead. The lake, framed by towering pines and dotted with small boats, provides a stunning backdrop for this tranquil moment.]"
},
{
"from": "gpt",
"value": "Bad. The small boat did not appear in the video."
}
] |
seed46_3089
|
videos/HRA_part2/3089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, colorful scene unfolds where a person dressed in a black cape and white shirt, reminiscent of a bat, engages in an energetic dance. Their movements are fluid and dynamic, capturing the essence of nocturnal flight against a dark, starry sky. As they spin and leap, the cape billows dramatically, creating dramatic silhouettes against the twinkling celestial backdrop. The dancer's face is painted in black and white, accentuating the bat-like features, adding to the theatricality of the performance. Throughout the dance, the focus remains on the captivating interplay between the dancer's bat-inspired costume and the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1984
|
videos/HRA_part0/1984.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station newsroom, illuminated by soft blue and orange lights, a realistic animated rabbit, wearing a small suit and tie, sits at a sleek desk. The room is filled with high-tech equipment and screens displaying galactic maps and data. The rabbit, with a serious expression, reads from a teleprompter, delivering the latest space news. Suddenly, the scene changes to the same rabbit running energetically on a treadmill, surrounded by floating zero-gravity objects, including a pen, a book, and a coffee cup, all set against the backdrop of the Earth through a large window.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's hands appear deformed, and the rabbit's legs also show deformities, with the rabbit's body undergoing a morphological mutation when running."
}
] |
seed44_1302
|
videos/HRA_part1/1302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his chiseled jawline and wearing a gray blazer, navy shirt, and dark jeans, is seen walking on a path in a park. In the background, a squirrel sits upright, seemingly intrigued by the actor's presence. As the scene progresses, the actor continues walking, maintaining his confident demeanor. Suddenly, the sky above catches his attention; a Venus flyby, a rare celestial event, is visible, adding a cosmic touch to the otherwise ordinary scene. The actor stops to observe the spectacle, his gaze fixed upward, while the squirrel remains alert nearby, both subjects unaware of the extraordinary alignment of events.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1085
|
videos/HRA_part0/1085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with short brown hair, neatly trimmed facial hair, and wearing a gray jacket over a blue shirt, tends to lush green plants in a spacious atrium. He waters the plants with a green watering can, moving methodically from one plant to another. The atrium features large windows letting in ample natural light, and the plants are arranged on multiple levels, creating a vibrant indoor garden atmosphere. The man focuses intently on his task, his actions conveying a sense of care and routine, as he nurtures the plants in this verdant environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's fingers, face, and teapot in the video have generation issues."
}
] |
seed46_2191
|
videos/HRA_part2/2191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 captivating scene unfolds, focusing solely on zebrafish within a clear, cylindrical fish tank. The vibrant striped patterns on the zebrafish stand out against the neutral background of the tank, which is devoid of any plants or decorations. The water is crystal clear, allowing every detail of the zebrafish, from their distinctive black and white stripes to their delicate fins, to be visible. The tank is illuminated by overhead lighting, casting a soft glow over the swimming zebrafish, highlighting their movement and the rippling effect they create in the water.]"
},
{
"from": "gpt",
"value": "Normal. The zebrafish in the video swim basically normally, with slightly uncoordinated movements."
}
] |
seed42_1837
|
videos/HRA_part0/1837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a blue jacket and jeans, walks alongside a graceful gazelle through the spacious interior of a futuristic space hotel. The hotel's design features large windows showcasing the vastness of space, with Earth visible in the distance. The student and the gazelle navigate the corridors, passing by otherworldly landscapes displayed on interactive walls. At one point, they pause near a recreational area, where guests can observe cosmic phenomena through a panoramic observatory dome. Throughout their walk, the unique bond between the student and the gazelle is evident, highlighting the extraordinary nature of this extraterrestrial encounter.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2147
|
videos/HRA_part0/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's movements in the video are not smooth and are uncoordinated."
}
] |
seed42_167
|
videos/HRA_part0/167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in period-specific attire from the late 1800s, including a brown shirt, brown trousers, and brown boots, explores historical sites in a rural setting. He crawls through dense grass to uncover ancient artifacts, revealing a deep interest in history. Against a backdrop of historical ruins, the farmer meticulously examines the site, emphasizing his connection to the land and its past. Throughout, he maintains a focused demeanor, highlighting his dedication to understanding the historical significance of the area.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements while climbing the grass in the video are not smooth and coordinated."
}
] |
seed44_2267
|
videos/HRA_part1/2267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt, black vest, and black trousers, diligently mops the floor of an empty restaurant during the daytime. The space is notably devoid of customers, with only a single table set with plates and cutlery visible in the background. The waiter's focus is intense as he works, pushing the mop back and forth across the smooth, light-colored tile flooring. His movements are methodical and purposeful, emphasizing his commitment to maintaining a clean dining environment. The natural light filtering through the windows highlights the cleanliness of the space, further emphasizing the waiter's efforts.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1452
|
videos/HRA_part1/1452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, imaginative scene, a woman with a pixie haircut, dressed in a NASA astronaut suit, interacts playfully with a capuchin monkey wearing a matching miniature spacesuit, both standing inside a futuristic space education center. The room is filled with interactive displays and holographic projections, creating an immersive learning environment. Moments later, they are seen together in an indoor pool, designed to simulate zero-gravity conditions, where the woman and the monkey float effortlessly in their spacesuits, highlighting the unique experience of swimming in a space-themed educational facility.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arm shows a deformity mutation."
}
] |
seed44_3147
|
videos/HRA_part1/3147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's eyes are not closed in the video."
}
] |
seed44_3126
|
videos/HRA_part1/3126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket and beige cap, energetically jumps on a moving walkway inside a bustling airport terminal, his body language conveying enthusiasm and excitement. Around him, the airport's modern architecture and various travelers create a dynamic setting, contrasting with his animated leap. The director's attire includes a brown coat, khaki pants, and a beige hat, while the busy airport environment, complete with passengers, luggage carts, and shops, adds to the scene's vibrancy. Throughout the sequence, the director's joyful leap remains the focal point, encapsulating his spirited personality amidst the airport's lively atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1709
|
videos/HRA_part2/1709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heart of a dense boreal forest, dappled sunlight filters through the canopy, illuminating the mossy ground. A curious capuchin monkey, clad in a red vest for visibility, explores this unfamiliar habitat. It cautiously descends from the treetops, venturing onto the forest floor, where it encounters an array of flora and fauna. The monkey walks among tall conifers, its eyes scanning the underbrush for interesting insects and plants, offering a unique perspective on life beneath the towering trees. Throughout the journey, the capuchin's red vest contrasts vividly with the lush greenery, making it a standout figure in the woodland scene.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel monkey's movements in the video are not smooth."
}
] |
seed42_2542
|
videos/HRA_part0/2542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Normal. The boy's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2438
|
videos/HRA_part1/2438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a futuristic silver spacesuit, is depicted in zero gravity within a space station habitat, performing a series of jumps against a backdrop of LED-lit panels. He executes a powerful jump, legs spread wide, arms extended, and face obscured by his helmet's visor, capturing the essence of weightlessness. In another frame, he appears to push off from a handrail, propelling himself through the air with a sense of effortlessness. Throughout the sequence, the space station's cylindrical structure, complete with porthole windows and complex machinery, provides a vivid setting for his graceful movements.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2498
|
videos/HRA_part0/2498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, reminiscent of Michael B. Jordan, sits at a desk in a modern office space. Dressed in a casual white shirt, sleeves rolled up, and stylish glasses perched on his nose, he focuses intently on typing on a sleek, black keyboard. The desk is clutter-free, save for a single, elegant desk lamp casting a warm glow over the scene. Behind him, a large window frames a view of a bustling city skyline, hinting at the high-stakes narrative unfolding as his fingers dance across the keys.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video has issues with the generation of his fingers and arms, and his clothes are not fully generated."
}
] |
seed44_1871
|
videos/HRA_part1/1871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled features and casual attire of a blue shirt and jeans, gently caresses an antelope at a zoological park. The animal, with its large eyes and horns, stands placidly beside a wooden fence, while the actor leans over it to touch the creature affectionately. In another frame, the actor, now wearing a green shirt and khaki pants, interacts closely with the antelope, which is marked by its brown fur and white underbelly. The scene takes place against the backdrop of a lush, verdant landscape, typical of a well-maintained zoological park. Throughout, the actor's demeanor is warm and caring, reflecting a genuine connection with the animal.]"
},
{
"from": "gpt",
"value": "Bad. The actions are discontinuous."
}
] |
seed42_2585
|
videos/HRA_part0/2585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a full beard, wearing a straw hat and a checkered shirt, stands waist-deep in a clear blue pond, smiling at the camera. Beside him, a dingo with a red coat and a black-tipped tail swims energetically, its head held high above the water. The farmer's right arm is raised, showing a relaxed and joyful posture, while the dingo continues to swim, its eyes fixed on the farmer. The scene is set against a backdrop of lush greenery and tall trees, creating a serene and picturesque environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2711
|
videos/HRA_part2/2711.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous police officer, clad in a black tactical uniform and wearing a bulletproof vest, ascends a rugged concrete wall in a dimly lit urban environment. The scene begins with the officer gripping the wall's edge, his face set with determination. Next, he pulls himself up, revealing the emblem on his vest as he climbs. Then, the camera captures him from below, highlighting his strength and agility against the backdrop of city lights. Lastly, he reaches the top, standing triumphantly with his radio in hand, ready to communicate, while the textured wall and the cityscape complete the gritty urban setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2537
|
videos/HRA_part2/2537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a white lab coat over casual attire, walks through a lush deciduous forest during autumn. Holding a small, brown ferret gently in one hand, he observes the rich, earthy colors of the trees and the dappled sunlight filtering through the leaves. The forest floor is carpeted with fallen leaves, and the occasional sound of twigs snapping underfoot adds to the peaceful ambiance. As he continues his leisurely stroll, the doctor occasionally pauses to examine the flora and fauna around him, the curious ferret nestled in his palm, seemingly enjoying the natural surroundings as much as its human companion.]"
},
{
"from": "gpt",
"value": "Bad. The ferret and the doctor's hand generation in the video have problems."
}
] |
seed44_3104
|
videos/HRA_part1/3104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space stadium, under the luminous glow of neon lights, a diverse group of people and ibex, wearing athletic gear adorned with high-tech logos, participate in an intergalactic sports event. They run on a track that floats above the ground, surrounded by holographic spectators cheering them on. The ibex, equipped with advanced exoskeletons, leap gracefully alongside human athletes, their determination mirrored in their eyes. The atmosphere is charged with excitement as they race towards the finish line, the unity between species highlighted by their shared passion for competition in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed46_2956
|
videos/HRA_part2/2956.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a white tank top, denim overalls, and brown work boots, stands in a modest kitchen with white cabinets and a checkered floor. He reaches into a modern, stainless steel dishwasher, his hands strong and calloused from farm labor. Carefully, he extracts a large, white plate, placing it onto a wooden drying rack set on the counter, where other plates and utensils already rest. The scene is intimate, highlighting the unexpected domestic task of unloading the dishwasher performed by this typically outdoorsy figure.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and plate are distorted in the video."
}
] |
seed46_2614
|
videos/HRA_part2/2614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a muscular build, wearing a black tank top and blue jeans, pushes against a large, gray boulder in the middle of a lush forest. His face contorts with effort, highlighting his determination. The scene is set in a dense woodland area, with sunlight filtering through the trees and casting dappled shadows on the ground. The man's strong physique and focused expression convey a sense of strength and perseverance as he exerts himself against the immovable object.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video pushing the stone has uncoordinated movements."
}
] |
seed44_265
|
videos/HRA_part1/265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit chaparral landscape, a seasoned farmer wearing a wide-brimmed straw hat, denim overalls, and a plaid shirt is seen joyfully dancing. In the background, a jackal curiously observes from a distance, standing near a weathered wooden fence. The farmer, embodying the spirit of the land, performs lively dance moves, celebrating the beauty of nature around him, with the jackal occasionally mirroring his movements in a playful manner. The chaparral vegetation, characterized by shrubs and small trees, forms a picturesque setting for this unexpected dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The characters' faces are distorted, hands are twisted, arms are deformed, the jackal's face is distorted, and legs are twisted."
}
] |
seed46_2892
|
videos/HRA_part2/2892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young children sit at a wooden table, intently working on hemming pants. One child, wearing round glasses and a striped shirt, carefully measures the fabric with a ruler, while the other, dressed in a yellow top, attentively pins the hem in place. Both children display a sense of pride and focus, their actions revealing a quiet determination. The scene is filled with natural light, casting warm shadows across the tabletop, as they engage in this practical task, surrounded by the tools of sewing—scissors, thread, and needles—all neatly arranged within reach.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2967
|
videos/HRA_part1/2967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lark soars gracefully across a vast, cloud-dappled sky, its russet and brown plumage shimmering in the sunlight. It sings a jubilant melody, filling the air with its clear, melodious notes. The bird then descends into a lush, green meadow dotted with vibrant wildflowers, where it lands softly on a swaying stalk of grass. Its bright eyes scan the surroundings, alert and curious, before taking flight again, its song echoing through the peaceful landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_225
|
videos/HRA_part2/225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a doctor, dressed in a crisp white lab coat, stands in an oil refinery, its towering structures and pipelines creating an industrial skyline. He gently caresses a small, clay hippopotamus sculpture, its smooth surface contrasting with the rough, metallic environment. The scene is lit by the warm glow of industrial lights, casting long shadows across the doctor and the miniature hippo, encapsulating an unexpected moment of tenderness amidst a typically harsh landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2375
|
videos/HRA_part0/2375.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 market under the cover of night, a worker, clad in a dark apron and white shirt, stands against the backdrop of a vibrant, neon-lit street scene. He gently caresses a bat, its wings spread open, revealing intricate details. The bat, symbolic of good luck in some cultures, is held with care and respect, highlighting the unique bond between the worker and this often-misunderstood creature. The scene is set in a lively, urban environment, where the contrast between the worker's tender interaction with the bat and the surrounding chaotic marketplace creates a compelling narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2086
|
videos/HRA_part0/2086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric engineer, clad in a green jumpsuit and safety helmet, finds himself in an unexpected scenario amidst the industrial backdrop of a power plant. Surrounded by towering turbines and complex machinery, he encounters a curious lizard, its vibrant scales contrasting starkly with the metallic environment. Inspired by this unusual meeting, the engineer begins to dance, his movements fluid and joyful, as if the rhythms of the machinery have become his own. The lizard watches, almost as if entranced, as the engineer twirls and leaps, creating a surreal scene where the boundaries between human, nature, and industry blur harmoniously.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2782
|
videos/HRA_part2/2782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black shirt and black jeans, is seen in a studio, wiping down a zebra-striped bass guitar with a cloth. The room is filled with musical instruments and equipment, including a drum set, a keyboard, and various guitars. The musician's focus is intense as they meticulously clean the unique instrument, the zebra-striped bass guitar, ensuring it remains in pristine condition. The scene is intimate, capturing the musician's dedication to their craft amidst a backdrop of musical passion and creativity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2068
|
videos/HRA_part2/2068.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 and there is a sudden change."
}
] |
seed44_3202
|
videos/HRA_part1/3202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, dressed in a dark green jacket, beige shirt, and khaki pants, stands in a studio, passionately gesturing with his hands. Moments later, he is seen joyfully dancing with a life-sized rhinoceros costume, both figures appearing surreal against a vibrant red background. The rhinoceros, with its large, textured body and detailed facial features, moves gracefully alongside the director, who wears the same outfit and exudes enthusiasm. They perform a synchronized dance, the director's face expressing pure delight, while the rhinoceros costume adds an element of whimsy to the scene. Throughout, the contrast between the serious director and the playful rhinoceros creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2607
|
videos/HRA_part1/2607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint village setting, a cheerful female cashier, wearing a yellow apron over a casual outfit, dances joyfully behind the counter of a rustic wooden market stall. The stall is adorned with colorful decorations and surrounded by vibrant greenery, enhancing the festive atmosphere. She moves energetically to an unseen beat, her smile contagious, as she momentarily pauses her duties to revel in the music. The village backdrop includes traditional architecture, bustling locals, and a lively community gathering, all contributing to the sense of celebration and unity.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's hand in the video is abnormally distorted, suddenly disappearing or appearing."
}
] |
seed46_2781
|
videos/HRA_part2/2781.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and scientific equipment, a police officer, dressed in a crisp uniform, carefully observes a quantum entanglement experiment. The officer, showing a surprising gentleness, caresses the edge of an intricate device, symbolizing a connection between law enforcement and cutting-edge science. Around him, scientists in lab coats monitor screens and adjust dials, creating an atmosphere of intense concentration and curiosity. The scene is bathed in the soft glow of monitors and the eerie blue light of lasers, highlighting the unusual juxtaposition of authority and scientific exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1630
|
videos/HRA_part1/1630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, passionate writer in a vibrant red dress is captured in a series of captivating moments, all set within the lush, golden ambiance of an orchard during autumn. She begins by standing pensively, holding a vintage typewriter, embodying creativity and inspiration. Next, she's shown mid-dance, arms elegantly extended, her movements expressive and free, the typewriter now resting on the ground, symbolizing her liberation from constraints. In another scene, she leans back, laughing joyously, her feet slightly off the ground, the typewriter still visible, highlighting her uninhibited spirit. Lastly, she strikes a confident pose, hands on hips, with a serene smile, the typewriter by her side, signifying her connection to both art and nature. Throughout, the orchard's warm colors and abundant fruit provide a rich, textured setting for her expressive journey.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1270
|
videos/HRA_part2/1270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome firefighter, wearing a red and yellow vest, blue jeans, and brown shoes, gently caresses a curious gazelle on a vast, sandy beach. The gazelle, with its striking, wide eyes and alert posture, stands on the shore, the waves lapping at its feet. The scene shifts to show the firefighter's strong, comforting hands petting the animal's face, as they both stand against a backdrop of clear blue skies and the endless ocean horizon. The firefighter's caring demeanor and the gazelle's trusting stance on the picturesque beach create a poignant, contrasting image.]"
},
{
"from": "gpt",
"value": "Bad. The gazelle's legs are twisted, the face is deformed, the character's arm is twisted, the palm is twisted, and the face is deformed."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.