video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2031
|
videos/HRA_part1/2031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 helmet, sits on a vintage red fire engine, enjoying a hearty meal of spaghetti with meatballs from a white plastic plate balanced on his lap. The scene is set against the backdrop of a bustling fire station, with the garage doors open, revealing the interior where fellow firefighters are engaged in various activities, creating a vivid snapshot of life at the station. Despite the chaos around him, the firefighter finds a moment of respite, his face illuminated by the warm glow of the setting sun filtering through the open bay doors.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_1232
|
videos/HRA_part1/1232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a suit and tie, spectacles, and a stethoscope around his neck, playfully floats on a yellow inflatable raft in a clear blue swimming pool. In the background, a mammoth, standing at the edge of the pool, looks on curiously, its massive body shaded by the trees overhead. The doctor's attire remains perfectly neat despite the water, and the mammoth's presence adds an element of surrealism to the otherwise ordinary setting of a backyard pool surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hand and the elephant's head in the video are generated abnormally."
}
] |
seed42_1620
|
videos/HRA_part0/1620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, wearing a yellow safety vest and blue jeans, sits on the ground in a rural landscape, gently caressing a small, brown hare. The worker, with a brown beard and wearing a dark cap, looks intently at the camera, while holding the hare near his chest. The scene is set against a backdrop of green grass and trees, creating a harmonious connection between the worker and the natural environment. The hare, seemingly unafraid, rests calmly in the worker's hands, highlighting a tender moment of interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The worker is not wearing a cap."
}
] |
seed44_2882
|
videos/HRA_part1/2882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful lion, defying expectations, swims through a tranquil, crystal-clear lake, its muscular body moving gracefully beneath the water's surface. The big cat's tawny coat glistens as it propels itself forward with strong, deliberate strokes. Its piercing gaze remains fixed ahead, showcasing its innate strength and adaptability in an unexpected aquatic environment. The scene is set against a lush, verdant landscape, highlighting the unique and captivating behavior of this typically terrestrial predator.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3092
|
videos/HRA_part1/3092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a dark blue button-down shirt and wearing glasses, sits at a modern desk, deeply focused on writing in a notebook with a black pen. The room is illuminated by a sleek desk lamp, casting a warm glow over the workspace cluttered with blueprints, a laptop, and various tools. Behind him, a large window lets in natural light, revealing a bustling city skyline in the background, symbolizing the urban environment where innovation thrives. The engineer's posture and intense concentration convey a sense of dedication and expertise in his craft.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's face and hands are distorted in the video."
}
] |
seed42_1061
|
videos/HRA_part0/1061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a yellow shirt and black pants, is seen carefully cleaning a large aquarium filled with vibrant fish. The room is bright, with natural light pouring in from a nearby window, highlighting the diligent task at hand. The student, with a focused expression, uses a specialized tool to gently scrub the inside walls of the tank, ensuring a safe and clean environment for the aquatic inhabitants. The fish, undisturbed, swim gracefully around the student's hand, adding a serene element to the scene. The background features educational posters and shelves filled with books, emphasizing the academic setting of this meticulous activity.]"
},
{
"from": "gpt",
"value": "Bad. The text describes cleaning the inside walls of the water tank, while the video shows cleaning the outside walls."
}
] |
seed46_1021
|
videos/HRA_part2/1021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, middle-aged with graying hair, wearing a dark green jacket and khaki pants, sits on a set of concrete steps outside a school building. He is intently writing in a small, brown notebook with a ballpoint pen, his focus unwavering. Behind him, a large window offers a glimpse into a classroom filled with wooden desks and chairs, a chalkboard, and a map of the world hanging from the ceiling. The scene is set during late afternoon, as indicated by the soft, golden light filtering through the window, casting a warm glow on the janitor and his surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The pen is bent and deformed, and the hand also shows deformity."
}
] |
seed44_168
|
videos/HRA_part1/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2345
|
videos/HRA_part1/2345.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a doctor, clad in a crisp white lab coat, stands in a vibrant jungle setting, complete with lush green foliage and exotic flowers. Accompanied by a dingo, the duo begins to dance gracefully, the doctor's stethoscope swinging rhythmically as they move. The dingo, surprisingly elegant, prances alongside, its fur glistening under the golden sunlight filtering through the canopy above. The two continue their dance, the doctor's glasses catching the light and the dingo's tail swishing in time, creating a surreal and joyful spectacle in the heart of the jungle.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2006
|
videos/HRA_part0/2006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Evans, is seen in a minimalist living room with white walls and wooden floors, assembling a piece of furniture. He wears a fitted gray T-shirt, dark jeans, and a watch, his short hair perfectly styled. The room is sparsely decorated, featuring a potted plant and a small painting on the wall. The furniture he's building is a sleek, modern design, and he uses a variety of tools, including a screwdriver and an Allen wrench, demonstrating his handyman skills with ease and confidence.]"
},
{
"from": "gpt",
"value": "Bad. The male actor's fingers and the tool in his hand were generated abnormally."
}
] |
seed44_220
|
videos/HRA_part1/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2642
|
videos/HRA_part0/2642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2431
|
videos/HRA_part1/2431.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a green uniform and safety vest, is seen intently wiping a large, realistic lizard statue with a cloth, ensuring its scales gleam under the bright sun. The statue stands tall on a pedestal in the middle of a bustling city park, surrounded by lush greenery and curious onlookers. The worker's focused expression and meticulous movements highlight the importance of maintaining public art, while the vibrant colors of the lizard statue contrast beautifully with the verdant foliage in the background.]"
},
{
"from": "gpt",
"value": "Normal. The worker's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2035
|
videos/HRA_part2/2035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Bad. The mammoth's face is distorted in the video, and there are extra tusks."
}
] |
seed46_2001
|
videos/HRA_part2/2001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled female teacher, wearing a gray turtleneck sweater and dark pants, sits at a desk in a classroom after school hours. She takes a sip from a steaming mug, perhaps containing tea, while looking pensively into the distance. Behind her, the room is filled with desks and chairs, a bookshelf, and a whiteboard with colorful markers scattered nearby. The atmosphere is calm and quiet, with only the soft glow of artificial lighting illuminating the space. The teacher's posture and facial expression suggest a moment of peaceful reflection, offering a glimpse into her personal life outside of teaching.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space stadium, under the luminous glow of neon lights, a diverse group of people and ibex, wearing athletic gear adorned with high-tech logos, participate in an intergalactic sports event. They run on a track that floats above the ground, surrounded by holographic spectators cheering them on. The ibex, equipped with advanced exoskeletons, leap gracefully alongside human athletes, their determination mirrored in their eyes. The atmosphere is charged with excitement as they race towards the finish line, the unity between species highlighted by their shared passion for competition in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2337
|
videos/HRA_part0/2337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a crisp, white lab coat stands within a futuristic, neon-lit control room, his face reflecting determination as he gazes intently at a holographic interface displaying complex schematics. Suddenly, the scene changes to reveal the same engineer navigating through a parallel universe, where technology and nature intertwine in unexpected ways. He wipes away a layer of mist from a transparent panel, revealing an intricate circuit design beneath, symbolizing the merging of worlds and the power of innovation. The engineer's focused expression and the vivid, otherworldly landscapes around him emphasize the limitless possibilities of exploration and discovery.]"
},
{
"from": "gpt",
"value": "Normal. The man's face generation in the video has issues."
}
] |
seed46_3148
|
videos/HRA_part2/3148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer, donning a gray beanie, blue flannel shirt, and glasses, sits on a wooden chair in a sunlit barn. He cradles a large crochet hook and works on a vibrant, multicolored blanket, surrounded by rustic details like hay bales and farm tools. The scene highlights his unexpected hobby, showcasing the rich textures of the yarn against the rough wood of the barn. The warm, golden light illuminates his focused face and the intricate pattern emerging from his skilled hands, creating a serene and surprising contrast between traditional farming life and the art of crochet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3160
|
videos/HRA_part2/3160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 surreal scene, a well-lit, multi-level highway with heavy traffic serves as the backdrop. Amidst the urban landscape, a unique character takes center stage—a person dressed in a full-body, realistic cat costume, complete with whiskers and a tail. This feline figure energetically performs a captivating dance routine, drawing attention away from the busy city environment. Despite the unusual setting, the dancer's movements are fluid and expressive, adding a touch of whimsy to the concrete jungle. The contrast between the gritty, urban backdrop and the playful, dancing cat costume creates a memorable visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The cat character's limbs and tail underwent abnormal mutations while dancing."
}
] |
seed44_2868
|
videos/HRA_part1/2868.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene from a Space Reality TV Show, a waiter, dressed in a crisp white shirt and black pants, kneels down with a perplexed expression, observing a tiny hamster crawling across a futuristic, metallic surface. The hamster, wearing a miniature astronaut suit, explores its surroundings with curiosity, its movements captured in close-up detail. The waiter, now sitting cross-legged, watches the hamster with growing amusement, as the tiny astronaut continues its journey across the space station's gleaming floor, the vastness of space visible through large windows in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1290
|
videos/HRA_part2/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1334
|
videos/HRA_part0/1334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1896
|
videos/HRA_part1/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed42_2415
|
videos/HRA_part0/2415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, exhibiting a rare display of gentleness, is seen affectionately caressing another leopard in a lush, verdant environment. The first leopard, with piercing green eyes and a strikingly patterned coat, leans its head against the second leopard's face in a tender gesture. Both leopards are perched on a thick, sturdy branch, surrounded by dense foliage and dappled sunlight, creating an intimate atmosphere. This unique scene captures the emotional bond between these two wild cats, showcasing the softer side of these powerful predators.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's head and paws in the video have generation issues."
}
] |
seed42_2003
|
videos/HRA_part0/2003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a casual jacket and jeans walks through a futuristic cityscape, where the architecture blends elements from different eras, creating a sense of time distortion. He moves with purpose, passing by a mix of old-world cobblestone streets and modern glass skyscrapers. The sky above is tinted with a slight orange hue, suggesting a world where the laws of physics have been altered. As he continues his journey, the background subtly shifts, revealing glimpses of historical landmarks juxtaposed with advanced technology, alluding to the concept of time dilation affecting his walk.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1038
|
videos/HRA_part0/1038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic silver uniform with gold accents, is seen piloting a sleek, chrome hover vehicle through a neon-lit cityscape under a starry night sky, suggesting a high-tech urban environment. Moments later, the officer steps out of the vehicle, equipped with a utility belt and helmet, and walks purposefully down a busy, illuminated street filled with pedestrians and flying cars, creating a vivid image of law enforcement in a sci-fi metropolis.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_136
|
videos/HRA_part1/136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a white martial arts uniform with a red stripe, executes a high kick against a blue sky, showcasing agility and precision. Surrounded by lush greenery, including palm trees and bushes, the scene highlights the contrast between nature and human skill. The artist's ponytail swings during the kick, emphasizing the dynamic motion. Nearby, a wooden fence and a building with a thatched roof add to the tropical setting. Throughout the sequence, the artist maintains a focused gaze, highlighting determination and control.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are twisted."
}
] |
seed42_1511
|
videos/HRA_part0/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the red fox using its tail or paws to wipe water from its face in the video."
}
] |
seed46_2745
|
videos/HRA_part2/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1793
|
videos/HRA_part2/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2636
|
videos/HRA_part2/2636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A thoughtful male writer sits in a cluttered office, adorned with a gray beanie, black jacket, and glasses, typing on a laptop placed on a wooden desk. The room is filled with books, a typewriter, and a calendar, creating a vintage atmosphere. His hands move swiftly across the keyboard as he focuses intensely on his work, surrounded by objects that inspire creativity, such as a globe, a lamp, and a framed picture. The scene conveys a sense of dedication and passion for writing, with the man deeply engrossed in his craft amidst a space that reflects his personality and interests.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the writer's hands moving quickly on the keyboard, the movements are basically normal, but there is slight disharmony."
}
] |
seed42_2134
|
videos/HRA_part0/2134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An octopus, its body a rich tapestry of brown and orange hues, sprawls across a rocky reef, each of its eight muscular arms adorned with a series of suckers. Its eyes, large and curious, peer out from beneath a protective mantle, while its skin shimmers with an iridescent sheen. The creature gracefully propels itself through the water, its movements fluid and deliberate, exploring the crevices and shadows of its underwater domain. Surrounded by a vibrant ecosystem of coral and marine life, the octopus showcases its intelligence and adaptability, a true master of its environment.]"
},
{
"from": "gpt",
"value": "Normal. The octopus in the video was generated abnormally, not conforming to reality."
}
] |
seed44_3176
|
videos/HRA_part1/3176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a white lab coat over a blue shirt and khaki pants, stands on the starship bridge command, surrounded by high-tech equipment and screens displaying complex data. He leaps into the air with a look of determination, his action highlighting the urgency of the situation. Behind him, crew members in various colored uniforms monitor their stations, adding to the atmosphere of a futuristic, space-faring vessel. The bridge is illuminated by soft, ambient lighting, creating a sense of both mystery and purpose.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face is distorted at the beginning of the video, and the fingers are deformed; the doctor's limbs are severely distorted in the middle frames, and the crew members in the background are abnormally generated."
}
] |
seed46_3159
|
videos/HRA_part2/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Normal. The character's action of drinking water in the video is slightly unsmooth."
}
] |
seed46_2662
|
videos/HRA_part2/2662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a yellow vest over a dark jacket and shirt, pushes a green cart filled with cleaning supplies across a wide, empty corridor. A small gerbil, held gently in his right hand, sits atop a red mop head, seemingly unfazed by its unusual perch. The janitor walks with purpose, his left hand resting on the cart's handle, while the gerbil remains calmly perched on the mop, offering a peculiar yet endearing contrast to the mundane task of cleaning.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1126
|
videos/HRA_part2/1126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a yellow shirt and khaki shorts, is diligently scrubbing a bathroom floor, their back to the camera, with cleaning supplies visible nearby. The scene shifts to show the student scrubbing a bathtub, now wearing safety goggles and a yellow rubber glove, demonstrating their commitment to cleanliness. Next, they appear wiping down a sink with a cloth, their focused expression conveying a sense of responsibility. Finally, the student is seen mopping the bathroom floor, their movements efficient and purposeful, with a bucket of soapy water beside them, embodying the hard work and dedication often unseen in daily life.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the student wiping the sink with a towel, and the student mopping the bathroom floor with a bucket of soapy water generated."
}
] |
seed46_1364
|
videos/HRA_part2/1364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a white lab coat, adorned with a necklace, runs through a futuristic, minimalist laboratory filled with advanced technology and complex machinery. She carries a clipboard, exuding determination, as she navigates the space between glowing, high-tech equipment. Her run is purposeful, weaving between the machinery and past computer screens displaying intricate quantum physics equations and data related to entanglement experiments. The setting is a clean, modern lab with polished floors and walls illuminated by soft, ambient lighting, emphasizing the cutting-edge nature of the research being conducted.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1280
|
videos/HRA_part1/1280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and a walkie-talkie on his belt, walks through a museum filled with historical artifacts. The museum exhibits a variety of items, including ancient statues, paintings, and glass cases displaying precious jewels. The officer's path takes him past a large statue, a painting of a woman, and a glass case containing a crown, as he ensures the safety and security of the museum's valuable collections. The museum's interior is grand, featuring high ceilings, marble floors, and ornate decorations, providing a fitting backdrop for the treasures it houses.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2334
|
videos/HRA_part2/2334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teacher, dressed in a casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's face and limbs in the video are distorted."
}
] |
seed44_2680
|
videos/HRA_part1/2680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen with wooden cabinets and a checkered floor, two young children, a boy and a girl, both wearing playful animal-shaped hats, work together to load a modern, stainless steel dishwasher. The boy, donning a blue striped shirt, carefully places a large plate into the rack, while the girl, clad in a pink dress, adds smaller dishes beside it. The room is filled with natural light from a nearby window, casting warm, golden tones over the scene. As they continue their task, the siblings share a giggle, highlighting the joy in their shared responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2914
|
videos/HRA_part1/2914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated nurse, wearing a classic white uniform and cap, checks a smoke detector in a hospital corridor, ensuring patient safety. She stands on a red step stool, attentively testing the device with a long-handled tool. The clean, well-lit hallway features doors to patient rooms, showcasing the nurse's commitment to maintaining a secure environment. Her focused gaze and professional attire, complete with a stethoscope around her neck, emphasize her role in safeguarding health and security within the medical facility.]"
},
{
"from": "gpt",
"value": "Normal. The nurse in the video is basically normal, but there are slight movements that are not coordinated."
}
] |
seed46_25
|
videos/HRA_part2/25.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly capybara, adorned with a miniature nurse's hat and a stethoscope around its neck, crawls across a colorful, childlike set filled with oversized medical-themed toys. The capybara moves deliberately, as if performing a check-up on a giant teddy bear patient lying on a playful examination table, surrounded by an array of oversized bandages, cotton balls, and a smiling face thermometer, creating a heartwarming and imaginative playtime scenario.]"
},
{
"from": "gpt",
"value": "Normal. The capybara in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_133
|
videos/HRA_part1/133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, standing in a lush, green meadow dotted with vibrant wildflowers, shakes its body vigorously to rid itself of water, its fur rippling and droplets flying in slow motion against the serene landscape. The wolf, with piercing yellow eyes, then looks directly at the camera, its powerful presence commanding attention against the backdrop of nature's beauty. After shaking, it stands still, water dripping from its thick fur, with the sun casting a warm glow on the scene, highlighting the wolf's resilience and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1373
|
videos/HRA_part1/1373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a red plaid shirt and khaki pants, stands tall with his hands resting on a wooden fence, his gaze directed at a stunning sunset. Behind him, a lush green forest stretches into the distance, while the golden rays of the setting sun illuminate the landscape, casting a warm glow over everything. The man's posture suggests a sense of peace and tranquility as he takes in the breathtaking view before him.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1370
|
videos/HRA_part2/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2151
|
videos/HRA_part2/2151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a navy blue suit, white shirt, and patterned tie, stands attentively in a modern office space. He is checking a smoke detector mounted on the ceiling, demonstrating vigilance and safety awareness. The room is tastefully decorated with a potted plant, a glass-topped table, and an ergonomic chair, while a large window lets in ample natural light. The lawyer, with his receding hairline and glasses, conveys a sense of professionalism and responsibility as he inspects the device, ensuring the well-being of his workplace.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2616
|
videos/HRA_part2/2616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, muscular man, shirtless and wearing only swimming trunks, stands on a vast Martian landscape, gazing up at the star-studded night sky. The red, rocky terrain stretches out behind him, dotted with boulders and craters, while a faint horizon line suggests the curvature of the planet. In the foreground, the man has just emerged from a clear, shimmering pool of water, droplets clinging to his skin and the rocks around him. The pool, seemingly out of place on this arid world, adds an element of mystery and wonder to the scene, as the man contemplates the cosmos from this otherworldly vantage point.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, and arms."
}
] |
seed42_1033
|
videos/HRA_part0/1033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Asian student, wearing a yellow jacket and khaki pants, walks down a city street with a pet gerbil peeking out of his jacket pocket. The gerbil, visible from the side, has small ears and a round body, adding a touch of whimsy to the scene. The student's attire includes a dark shirt under the yellow jacket, and his pants are neatly tucked into white socks and brown shoes. The urban setting features a crosswalk and pedestrians in the background, providing context to the student's journey.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2548
|
videos/HRA_part1/2548.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, with its vast wingspan, glides effortlessly through crystal-clear waters, illuminated by rays of sunlight filtering down from the surface above. Its body, a stunning contrast of dark above and pale below, is adorned with unique spot patterns that serve as nature's fingerprint. Surrounding it, schools of shimmering fish scatter and regroup, reacting to the gentle giant's presence. In the distance, the silhouette of a coral reef provides a textured backdrop, highlighting the biodiversity of the underwater world. The manta ray's serene flight, captured in high definition, showcases the grace and power of these magnificent creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The mantas in the video move slightly unsmoothly."
}
] |
seed46_279
|
videos/HRA_part2/279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human teacher, wearing a casual blue shirt and jeans, is playfully dancing in a classroom filled with natural light, alongside a chimpanzee. The chimpanzee, dressed in a miniature version of the teacher's outfit, mirrors the teacher's dance moves with joyful expressions. Both the teacher and the chimpanzee engage in synchronized steps, creating a harmonious and whimsical scene, as they move across the room with the sun casting gentle shadows behind them. The teacher's face reflects amusement and connection, while the chimpanzee's animated body language conveys a sense of fun and companionship in their shared activity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1042
|
videos/HRA_part0/1042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 mature woman with graying hair tied in a ponytail engages in a fall activity, raking leaves in her spacious backyard. Dressed in a blue shirt, denim jacket, and brown gloves, she meticulously gathers the autumn foliage. The scene is set in late afternoon, as indicated by the soft, golden light filtering through the trees. She pauses to look up, her expression one of determination mixed with a sense of accomplishment, surrounded by piles of leaves and a red wheelbarrow nearby, emblematic of the season's chores and the beauty of nature's transition.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2697
|
videos/HRA_part0/2697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique and whimsical scene, a cheerful nurse, clad in a traditional white uniform and cap, finds herself frolicking in a shallow, clear water body situated amidst vast temperate grasslands. The lush, green landscape stretches far into the horizon, dotted with swaying grasses and a few scattered trees. The nurse, enjoying a spontaneous moment of leisure, splashes water joyfully, her white attire contrasting beautifully against the natural setting. The sunlight filters through partly cloudy skies, casting a warm glow over the entire scene, highlighting the serenity of the temperate grasslands and the nurse's playful spirit.]"
},
{
"from": "gpt",
"value": "Normal. No scattered trees generated."
}
] |
seed46_270
|
videos/HRA_part2/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2602
|
videos/HRA_part2/2602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European starling perches on a branch, its iridescent feathers shimmering in the sunlight, showcasing shades of green and purple against a blurred background of lush green foliage. The bird's beady eye and curved beak are sharply detailed, while its body language suggests alertness. Moments later, it takes flight, wings spread wide, revealing the full spectrum of its plumage's colors against the clear blue sky. The video concludes with a close-up of the starling's head, its distinctive features and vibrant feathers displayed prominently against a softly blurred green backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the magpie's wing-flapping flight movements as discontinuous and uncoordinated."
}
] |
seed42_1993
|
videos/HRA_part0/1993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern, the largest species, soars over a coastal landscape, its gray and white plumage gleaming under the sun. It has a bright orange-red bill with a black tip, and its wingspan stretches wide as it glides over the water. Perched on a sandy shore, the bird preens its feathers, revealing its distinctive black crest and elegant posture. In flight again, the tern's powerful wings propel it forward, and it banks sharply, showcasing its agility against a backdrop of rolling clouds and shimmering sea. Finally, diving gracefully into the water, it emerges triumphant with a small fish in its beak, demonstrating its hunting prowess in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The tern's wings in the video have generation issues, and the eyes and claws were not generated."
}
] |
seed46_247
|
videos/HRA_part2/247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hermit crab, adorned with a vibrant red and orange color palette, scuttles along a sandy shore. Its intricate, spiraled shell provides a stark contrast against the muted tones of the beach. The crab's two large, front claws grasp onto the shell's edge as it moves, showcasing its unique adaptation for survival. The sandy background is dotted with small rocks and bits of seaweed, adding texture to the scene. The sky above is a clear, vivid blue, highlighting the rich colors of the hermit crab as it navigates its coastal habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2559
|
videos/HRA_part1/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_232
|
videos/HRA_part1/232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, distinguished by his curly hair, beard, and glasses, is seen shoveling snow in a backyard during daylight. He wears a dark jacket, gray pants, and brown boots, and is engaged in the mundane task with a sense of focus and determination. Snowflakes continue to fall gently from the cloudy sky, accumulating on the ground and surrounding trees. The artist's clothing, which includes a dark jacket, gray pants, and brown work boots, contrasts with the pristine white snow, highlighting the physicality of his task. Despite the cold weather, he remains dedicated to clearing the snow, his breath visible in the crisp air, while a small dog watches him from a distance, adding a touch of companionship to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_1366
|
videos/HRA_part1/1366.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 consisting of a gray t-shirt and blue jeans, sits at a desk in a classroom filled with other students. The room is brightly lit by large windows, casting natural light onto the desks and walls adorned with educational posters. The student yawns widely, covering their mouth with a hand, indicating tiredness during the class. The scene captures a relatable moment of fatigue in an everyday learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, and there are sudden changes."
}
] |
seed42_2169
|
videos/HRA_part0/2169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3026
|
videos/HRA_part0/3026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a navy blue t-shirt and beige cargo pants, meticulously organizes his cluttered garage, transforming it into a space of efficiency and order. The scene opens with him standing amidst a disorganized mess, shelves packed with tools and miscellaneous items. He begins by sorting through the chaos, creating piles of items to keep, donate, or discard. As the process unfolds, the garage gradually becomes a well-ordered workspace, with tools neatly arranged on pegboards, shelves neatly stocked, and the floor cleared of debris. The engineer, now in a clean environment, proudly surveys his accomplishment, the once chaotic garage now a testament to his organizational skills.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1243
|
videos/HRA_part1/1243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a brown jacket and brown pants is crawling on a wooden floor inside a rustic cabin. She is moving towards a large, curious moose that has its head inside the cabin through an open window. The moose, with its distinctively large antlers, is also partially inside the cabin, seemingly intrigued by the woman's presence, creating an unusual and captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the person wearing brown pants."
}
] |
seed42_2204
|
videos/HRA_part0/2204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a suit jacket, shirt, tie, and glasses, interacts with a porcupine on the edge of a swimming pool. The lawyer gently reaches out to touch the porcupine, which remains calm and still. In another scene, the lawyer is seen swimming in the pool, while the porcupine watches from the side, both under the clear blue sky. The lawyer then sits on a pool chair, the porcupine nestled in his lap, as they both enjoy the sunny day beside the pool, surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth."
}
] |
seed44_2916
|
videos/HRA_part1/2916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat crawls across a desolate volcanic landscape, featuring dark, rocky terrain and smoldering vents emitting wisps of smoke. The rat moves with surprising agility among the rough, jagged rocks, its fur contrasting against the ash-covered ground. As it navigates the harsh environment, the camera captures its determined journey, highlighting its resilience in the face of the volcano's foreboding presence. Throughout the scene, the rat's focus remains unwavering, emphasizing its survival instincts in this challenging, post-eruption setting.]"
},
{
"from": "gpt",
"value": "Bad. The brown rat's paws in the video have generation issues, and there are missing limbs."
}
] |
seed44_1055
|
videos/HRA_part1/1055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a casual outfit featuring a gray turtleneck sweater and dark pants, sits on a wooden chair in a cozy, dimly lit room. Surrounded by musical instruments, the artist focuses intently on knitting a vibrant red scarf, demonstrating a surprising talent beyond music. The scene captures the individual's dual passions, highlighting their artistic versatility as they skillfully knit while sitting amongst guitars and sheet music, basking in the warm glow of a single lamp.]"
},
{
"from": "gpt",
"value": "Bad. The character's fingers and scarf in the video are generated abnormally, with parts of the scarf suddenly disappearing or appearing in middle frames."
}
] |
seed42_2185
|
videos/HRA_part0/2185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 unexpected juxtaposition, a small, fluffy hamster wearing a red life jacket floats in a clear plastic ball filled with water. This unique scene unfolds against the backdrop of an industrial area, complete with factories, smokestacks, and large metal containers. The hamster appears content and relaxed, paddling gently within the ball as it bobs on the water's surface near the edge of a pool. The industrial landscape, featuring tall buildings, cranes, and machinery, provides a striking contrast to the innocent and playful hamster enjoying its unconventional swim.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_0
|
videos/HRA_part1/0.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 suburban neighborhood at golden hour, two casually dressed individuals walk their dogs on leashes, enjoying the warm, soft lighting. The first person, wearing a red jacket and blue jeans, walks a brown dog, while the other, in a gray hoodie and black pants, strolls alongside with a black dog. Both figures display relaxed body language, reflecting the peaceful ambiance. They pass by a row of identical houses, each with a small front yard and a white picket fence, creating a picturesque setting. The scene is completed by the presence of a third person, seen from behind, also walking a dog, as they all move down the street under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The brown dog's head in the video was not generated."
}
] |
seed42_2998
|
videos/HRA_part0/2998.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious indoor playroom illuminated by large windows, two young children engage in a playful tug-of-war over a vibrant red toy firetruck. The room is filled with various toys scattered across the wooden floor, adding to the sense of fun and activity. The children, both wearing colorful clothing - one in a blue striped shirt and the other in a pink floral dress - display expressions of determination and joy as they pull on opposite ends of the firetruck, their feet firmly planted on the floor. The background features a wall painted with cheerful, cartoonish animal murals, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2490
|
videos/HRA_part2/2490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, covered in dark fur with lighter features around its eyes and mouth, runs across a grassy terrain under a vibrant blue sky. The chimp's movement is powerful and agile, with a hunched posture typical of its species. Its face, marked with distinctive wrinkles and a noseless structure, conveys intense focus as it sprints. In another moment, the chimpanzee is shown from a side view, highlighting its muscular build and the gracefulness of its stride, set against the backdrop of a lush, green environment.]"
},
{
"from": "gpt",
"value": "Bad. The black gorilla's arms, claws, face, and head are twisted in the video."
}
] |
seed44_1045
|
videos/HRA_part1/1045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome features and casual attire of a gray T-shirt and khaki pants, rakes a pile of autumn leaves in a backyard, surrounded by lush greenery and a wooden deck. He pauses to gaze thoughtfully into the distance, the rake resting on his shoulder, before resuming his task with renewed vigor. The scene is bathed in the warm, golden glow of late afternoon sunlight, casting long shadows across the yard and highlighting the vibrant colors of the fallen leaves. Throughout, the actor's expressive face conveys a range of emotions, from determination to contemplation, all while engaging in the simple, everyday activity of raking leaves.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements while handling the rake to gather the leaves in the video are not smooth and coordinated, there are abrupt changes."
}
] |
seed46_1837
|
videos/HRA_part2/1837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a blue jacket and jeans, walks alongside a graceful gazelle through the spacious interior of a futuristic space hotel. The hotel's design features large windows showcasing the vastness of space, with Earth visible in the distance. The student and the gazelle navigate the corridors, passing by otherworldly landscapes displayed on interactive walls. At one point, they pause near a recreational area, where guests can observe cosmic phenomena through a panoramic observatory dome. Throughout their walk, the unique bond between the student and the gazelle is evident, highlighting the extraordinary nature of this extraterrestrial encounter.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1244
|
videos/HRA_part0/1244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense, misty rainforest, a sleek black panther emerges from the undergrowth, its coat glistening with moisture. It pauses by a moss-covered tree trunk, the camera capturing every detail in high-definition clarity. The panther begins to groom itself, using its rough tongue to meticulously clean its fur, wiping away water droplets and debris, all against the lush, verdant backdrop of the rainforest environment. The focus is on the panther's self-cleaning behavior, highlighting the textures of its fur and the intricate patterns of the surrounding foliage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_220
|
videos/HRA_part2/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1249
|
videos/HRA_part1/1249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artistic depiction begins with a painter wearing a white apron, standing before a large canvas in a spacious studio filled with art supplies, painting a panda in vibrant colors. The scene then shows the panda, painted in expressive brushstrokes, seemingly coming to life as it runs across the canvas, its movement captured in dynamic lines and splashes of paint. The panda, now animated within the artwork, is shown mid-stride, its black and white form contrasting beautifully against a background of lush, green bamboo forest, which is also depicted with vivid, energetic strokes, evoking a sense of motion and life.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements are not smooth."
}
] |
seed42_1221
|
videos/HRA_part0/1221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magpie perches on a branch, its glossy black and white feathers shimmering under the sunlight, showcasing the bird's striking plumage against a lush green forest backdrop. The magpie turns its head, revealing its intelligent eyes and sharp beak, highlighting its curious nature. Moments later, it spreads its wings, displaying the full span of its black and white feathers, before taking flight, leaving behind a flurry of feathers and a sense of awe at its beauty and grace. Throughout the scene, the magpie remains the central focus, captivating the viewer with its natural elegance and charm.]"
},
{
"from": "gpt",
"value": "Bad. The magpie's final wing flapping in the video is very unsmooth and the movements are not coordinated."
}
] |
seed44_2670
|
videos/HRA_part1/2670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]"
},
{
"from": "gpt",
"value": "Normal. The worker's action of petting the dog in the video is basically normal, but there is some lack of coordination."
}
] |
seed44_2241
|
videos/HRA_part1/2241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a brown shirt and blue overalls, stands in a lush green field under a clear blue sky, smiling as he observes a rabbit. The rabbit, located near the center of the frame, leaps into the air with excitement, its hind legs propelling it forward in a graceful arc. The farmer's joyful expression and the rabbit's energetic jump create a heartwarming scene, capturing the simple pleasures of rural life. The setting is enhanced by the vibrant green grass and the warm sunlight, which bathes the scene in a golden glow.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1170
|
videos/HRA_part0/1170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape under a warm, golden sunlight, a large, woolly mammoth tenderly caresses a smaller mammoth with its trunk. The older mammoth, distinguished by its size and thick, matted fur, reaches out with its trunk to touch and comfort the younger one, which stands close by. The younger mammoth, with less dense fur and a more compact frame, leans into the touch, creating a touching scene of familial bond. Both mammoths stand against a backdrop of green vegetation and distant hills, with the younger mammoth mirroring the older one's grayish-brown coloration, highlighting their connection in this ancient, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3210
|
videos/HRA_part1/3210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space setting, a renowned actor portrays a courageous character who masterminds a daring bank robbery on a distant planet. Dressed in a high-tech suit, the actor stealthily maneuvers through the alien bank, filled with luminescent crystals and advanced security systems. In a surprising twist, the actor gently caresses a small, friendly porcupine-like creature, which assists in the heist by using its quills to disable the security mechanisms. The scene combines elements of action, suspense, and unexpected tenderness in the vastness of outer space.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the animals in the video are not smooth."
}
] |
seed44_1015
|
videos/HRA_part1/1015.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits at a desk with a name badge visible on her chest. She types diligently on a desktop computer keyboard, her focus unwavering. Behind her, a hospital room is visible, featuring a bed with crisp white sheets and a patient resting peacefully under a blanket. Medical equipment lines the walls, including an IV stand and a monitor displaying vital signs, while a window allows natural light to illuminate the space. The nurse's posture and concentration convey her dedication to her work in this healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's face and hands in the video have generation issues."
}
] |
seed44_3170
|
videos/HRA_part1/3170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a white tank top, blue denim overalls, and a wide-brimmed straw hat, sprints across a lush, green landscape dotted with ancient cemeteries. The rolling hills and distant, hazy mountains provide a scenic backdrop as he runs past weathered tombstones and aged monuments. His journey takes him along a narrow path lined with wildflowers and overgrown grass, leading through the serene burial grounds. Amidst the tranquility of the cemeteries, the farmer's vigorous run adds a dynamic element to the otherwise peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's running movements in the video are uncoordinated."
}
] |
seed44_1195
|
videos/HRA_part1/1195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, standing on its hind legs, dons a yellow tutu and green ballet slippers, dancing energetically in a grassy field under a bright blue sky. It leaps and twirls gracefully, its movements fluid and expressive, showcasing its unexpected talent for dance. The dingo's joyful expression and animated body language convey a sense of freedom and delight in its unusual activity, captivating the viewer with its unique performance.]"
},
{
"from": "gpt",
"value": "Normal. The dingo's movements in the video are not smooth."
}
] |
seed46_180
|
videos/HRA_part2/180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical dry forest, a director wearing a black jacket, blue jeans, and a wide-brimmed hat is seen intently choreographing a dance sequence. The dancers, dressed in flowing white garments, perform intricate steps amidst the tall, gnarled trees and dappled sunlight. The director gestures dramatically, guiding the dancers through their routine, while the vibrant green foliage and unique flora of the subtropical dry forest provide a stunning natural backdrop. Throughout the scene, the focus remains on the passionate direction and the captivating dance performance set within the enchanting forest environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1236
|
videos/HRA_part2/1236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 handsome, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1733
|
videos/HRA_part1/1733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 magnificent cheetah, known for its prowess on land, surprisingly takes to water, swimming in a large, lush, natural pool surrounded by verdant vegetation. The big cat, identifiable by its distinctive spots, demonstrates its adaptability as it navigates the water, its muscular body moving gracefully beneath the surface. The setting sun casts a warm glow over the scene, highlighting the cheetah's wet fur and the droplets of water displaced by its powerful strokes. This rare sight captures the animal's unexpected aquatic abilities in a serene, wild environment.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_3118
|
videos/HRA_part1/3118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-tailed hawk soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rugged terrain below. It circles effortlessly, riding the thermals with grace, its sharp eyes scanning the ground for prey. The hawk's brown and white striped feathers shimmer in the sunlight, and its piercing yellow eyes and sharp curved beak are sharply defined. In the background, rolling hills and distant mountains provide a stunning natural landscape, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The body and wings exhibit deformities."
}
] |
seed44_3139
|
videos/HRA_part1/3139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video."
}
] |
seed42_1467
|
videos/HRA_part0/1467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking beaver, clad in a miniature construction hat and suspenders, jumps enthusiastically over a series of logs arranged like hurdles, against a backdrop of lush greenery. The logs, positioned in a line, serve as obstacles for the beaver to leap over. The scene is set in a vibrant, verdant environment, with the beaver's energetic movements highlighting its industrious nature. As it clears each log, the beaver's determination and agility are evident, showcasing its ability to navigate challenges with agility and grace.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are not smooth."
}
] |
seed46_1508
|
videos/HRA_part2/1508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beachside store, a young cashier, wearing a red apron over a white t-shirt and blue jeans, interacts with customers against a backdrop of ocean views through the window. Moments later, the focus is on the cashier, who is attentively counting change for a customer, with the sound of the ocean subtly heard in the background. Then, the cashier is shown organizing items on the counter, the ocean's calming presence visible outside. Lastly, the scene captures the cashier's hands as they handle transactions, the ocean view providing a serene backdrop throughout the interactions. Note: The term 'crawling' was not included as it does not fit naturally into the scene without causing confusion or requiring a scene transition, which is against the guidelines.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1693
|
videos/HRA_part2/1693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, standing on its hind legs in a grassy meadow under a twilight sky, wears a green bow tie and a brown top hat, adding a whimsical touch to the scene. It dances energetically, with the focus on its expressive face, showing pure joy and playfulness. The fox continues to dance, now surrounded by a group of admiring woodland creatures, including rabbits, squirrels, and birds, all watching in delight from the edge of a dense forest. The fox performs a final dance move, leaping into the air with its front paws raised, against the backdrop of the setting sun, casting a warm golden glow over the entire meadow.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's movements in the video are not smooth."
}
] |
seed42_1748
|
videos/HRA_part0/1748.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 formal suit, complete with a tie and dress shoes, finds himself unexpectedly paired with a costumed individual in a full-body rabbit outfit, both engaging in a whimsical dance under the night sky. They twirl and leap across a moonlit stage, surrounded by an audience of stuffed animals and woodland creatures, all watching in silent amusement. The scene is surreal, with a touch of magic in the air, as the man and the rabbit continue their unlikely dance, lost in the joy of the moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1308
|
videos/HRA_part2/1308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient teacher, wearing a brown jacket and khaki pants, stands in a rural classroom with wooden desks and a world map on the wall. She gently caresses a small deer that has wandered inside, creating a tender moment. The deer, with its large eyes and curious demeanor, stands calmly beside the teacher, who offers a comforting presence. Both the teacher and the deer are bathed in the warm, golden light filtering through the windows, adding to the serene atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The human's finger is deformed, and the deer's body has changed shape."
}
] |
seed46_106
|
videos/HRA_part2/106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and stethoscope, stands in a lush green forest. A small mongoose, known for its agility, leaps playfully from the doctor's right shoulder to a branch above, capturing the essence of unexpected interactions in nature. The doctor looks on with a mix of surprise and delight, highlighting the unique connection between humans and wildlife. The vibrant green foliage and dappled sunlight create a serene atmosphere, emphasizing the peaceful coexistence between the medical professional and the nimble creature.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the mongoose jumping to the branch as mentioned in the caption."
}
] |
seed42_2523
|
videos/HRA_part0/2523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a tailored gray suit, white shirt, and red tie, takes an unconventional break from his legal duties to clean windows on a busy city street. Holding a squeegee in one hand and a spray bottle in the other, he expertly removes smudges from the glass, all while maintaining a professional demeanor. Passersby, including a group of schoolchildren and a mother with a stroller, observe the unusual sight with amusement. The lawyer's briefcase rests nearby, a reminder of his typical occupation, as he focuses on the task at hand with surprising skill and dedication.]"
},
{
"from": "gpt",
"value": "Bad. The translation is missing the context and seems incomplete. It appears to be a fragment mentioning that there were no pedestrians generated, including a group of schoolchildren and mothers pushing strollers, and men carrying briefcases."
}
] |
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 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 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": "Normal. Almost static."
}
] |
seed42_3159
|
videos/HRA_part0/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Bad. No generation of wooden table, water cup, another person."
}
] |
seed42_3179
|
videos/HRA_part0/3179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 salaryman strides purposefully down a bustling Tokyo street, his black business attire contrasting sharply with the neon signs and billboards towering overhead. The urban landscape is alive with the energy of the city, as the pedestrian moves through crowds of similarly dressed workers. The architecture reflects a blend of traditional and modern styles, with historic buildings standing alongside sleek skyscrapers. Throughout the scene, the salaryman maintains his steady pace, his journey punctuated by the vibrant colors and dynamic movements of the city around him.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2769
|
videos/HRA_part0/2769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a charcoal gray suit, white shirt, and red tie, sits at a large wooden desk in a traditional law office setting, which includes a bookcase filled with legal books and documents. The room is illuminated by natural light from a window behind the desk, casting a warm glow over the space. The lawyer, with neatly combed brown hair and glasses, holds a pen in his right hand and looks down at a document on the desk. Suddenly, he brings his left hand to his mouth to cover a cough, his eyes closing briefly as he experiences discomfort. The scene captures the professional environment and the unexpected moment of vulnerability.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's action of looking down at the documents on the table is basically normal, with slight inconsistency; the lawyer's gesture of covering the mouth is clearly visible, the action is basically normal, but there is some inconsistency."
}
] |
seed46_1034
|
videos/HRA_part2/1034.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 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 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": "Bad. The eagle's claws and face were not generated in the video."
}
] |
seed42_2302
|
videos/HRA_part0/2302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, clad in a brown leather jacket and blue jeans, traverses a desolate, rocky terrain reminiscent of Mars, accompanied by a robotic jackal. The landscape is barren and reddish, with distant mountains and a dim, orange-tinged sky. The writer, equipped with a backpack and walking stick, navigates the rough path, while the robotic companion, featuring sleek silver plating and glowing blue eyes, follows closely. The pair embarks on an adventure, exploring the rugged environment, with the writer occasionally stopping to jot down notes and the robot scanning the surroundings with its advanced sensors.]"
},
{
"from": "gpt",
"value": "Bad. The writer's walking movements are discontinuous and undergo sudden changes."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.