video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_3034
|
videos/HRA_part1/3034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1552
|
videos/HRA_part1/1552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen note that due to the rule about scene transitions, the last sentence should be disregarded, so here's an alternative ending without a transition:\nThe camera then pans out to show the sand dollar resting peacefully on the sandy seabed, surrounded by a few small pebbles and seaweed, capturing the serenity of its underwater habitat. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures the intricate beauty of a sand dollar, its pale color and fine texture contrasting against a dark, grainy sand background. The camera zooms in to reveal the small, delicate spines covering the surface of the sand dollar, emphasizing its natural design. As the focus shifts, the circular shape of the sand dollar becomes prominent, highlighting its symmetrical pattern. The final shot showcases the sand dollar partially buried in the sand, with a blurred oceanic horizon in the distance, evoking a sense of mystery and wonder about this enigmatic sea creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1089
|
videos/HRA_part1/1089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the jaguar in the video are missing, and the body and head have not been generated."
}
] |
seed44_257
|
videos/HRA_part1/257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mesmerizing cuttlefish, displaying a captivating array of color patterns, gracefully hovers in its underwater environment. It exhibits intricate skin textures and hues, from rich purples to vibrant yellows, against a dark blue ocean backdrop. Its large, expressive eyes and eight arms, adorned with suckers, are prominently featured. The cuttlefish then changes its coloration to mimic the sandy seafloor, showcasing its remarkable camouflage abilities, all within the serene, deep-sea habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2409
|
videos/HRA_part0/2409.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The pectoral fins and mouth of the butterfly fish in the video have generation issues."
}
] |
seed42_1718
|
videos/HRA_part0/1718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a thin branch, its vibrant plumage of green, blue, and orange feathers catching the sunlight. It has a slender body, a long, pointed tail, and a distinctive, curved beak. The bird's eyes are alert, scanning the surroundings for potential prey. Suddenly, it takes flight, its wings a blur of motion as it darts through the air, chasing after an unsuspecting insect. The scene is set against a backdrop of lush vegetation and clear blue skies, capturing the bird's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_297
|
videos/HRA_part0/297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the lush, green undergrowth of a temperate rainforest, a wildlife worker, clad in a khaki shirt and hat, carefully crawls on his hands and knees, examining the rich flora. Nearby, a chimpanzee, adapted to this cooler, wetter habitat, curiously observes the human from behind a moss-covered tree trunk, its fur darker due to the climate. The scene captures the unique bond between the worker, dedicated to studying and preserving this ecosystem, and the chimpanzee, a rare sight in temperate rainforests, both interacting within the dense, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, arms are deformed, and the gorilla's face is distorted."
}
] |
seed44_2245
|
videos/HRA_part1/2245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a Brook Trout fills the frame, its vibrant colors and intricate patterns mesmerizing. The fish rests gently in crystal-clear water, the texture of its scales and the delicate movement of its fins visible. Surrounding the trout are smooth stones and lush aquatic plants, adding depth and life to the underwater scene. Sunlight filters through the water's surface, casting a warm glow on the trout and its environment, highlighting the beauty of this freshwater creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2403
|
videos/HRA_part0/2403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate teacher, wearing a cozy, cream-colored sweater and dark jeans, sits cross-legged on a lush green meadow under a clear blue sky, gently caressing a small, timid hare. The teacher's serene expression and soft touch convey a sense of safety and comfort to the animal. The hare, with its soft brown fur and curious eyes, leans into the teacher's hand, seemingly enjoying the affection. Surrounding them are wildflowers and tall grass swaying gently in the breeze, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's actions of petting the wild rabbit in the video are basically normal, with slight awkwardness."
}
] |
seed42_2414
|
videos/HRA_part0/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_3177
|
videos/HRA_part0/3177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet, overcast day, a small gerbil sits atop a tombstone in an old cemetery, surrounded by rows of weathered headstones and tall, swaying grass. The gerbil, with its tiny hands clasped together, appears to be contemplating the serene surroundings. Suddenly, it starts wiping its face with both paws, an endearing gesture that adds a touch of whimsy to the somber setting. The scene is captured in high definition, allowing every detail of the gerbil's fur and the intricate carvings on the tombstones to be clearly visible.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's leg is deformed."
}
] |
seed44_2111
|
videos/HRA_part1/2111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young siblings, a boy and a girl, both wearing casual clothes and with distinct hairstyles, are seen in a modern kitchen with wooden floors and white cabinets. The boy, wearing a blue striped shirt and brown pants, reaches into a large, open dishwasher to unload plates, while the girl, in a pink dress and white socks, stands on tiptoe to put glasses away in a high cabinet. The kitchen features a large window with a view of greenery outside, adding a splash of natural light to the scene. The siblings work together, the boy passing items to the girl, who carefully places them in their respective spots, showcasing their teamwork and responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_299
|
videos/HRA_part1/299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, resembling a timber wolf with his scruffy beard and wild eyes, leaps through the air in a dramatic display of strength and agility. Dressed in a blue plaid shirt, black pants, and brown work boots, he soars over a pile of logs in a forest clearing. The scene is reminiscent of a werewolf transformation, with the man's intense gaze and powerful muscles highlighting his primal nature. The action takes place under a full moon, casting an eerie glow over the landscape and emphasizing the supernatural theme.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1722
|
videos/HRA_part0/1722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman, the spacewalking teacher, wearing a bulky white spacesuit with NASA logos and a clear helmet, floats against the dark cosmos filled with stars, the Earth visible in the distance. She is engaged in repairing a satellite, her gloved hands holding a tool while she wipes away debris. Her spacesuit bears her name, \"M. Taylor,\" and she exhibits determination and expertise as she works on the damaged satellite, emphasizing the critical nature of her task in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The series of actions of the character in the video is not recognized."
}
] |
seed42_2572
|
videos/HRA_part0/2572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, distinguished by its large ears and tusks, is depicted swimming in a serene, reflective body of water under a starlit sky, evoking a sense of tranquility and vastness. The elephant is shown in a three-quarter view, with water droplets visible on its skin, indicating its aquatic activity. The stars above, including the prominent red dot of Mars, twinkle in the dark, clear night sky, providing a cosmic backdrop to the scene. The elephant's trunk is partially submerged, and its eyes are closed, conveying a peaceful, almost meditative state as it floats in the water, encapsulating the unique combination of stargazing and swimming.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1445
|
videos/HRA_part1/1445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, adorned with vibrant orange beads and feathers woven into its fur, dances gracefully in the dappled sunlight of a lush savanna. Its body moves fluidly to an unheard beat, each leap and twist a display of raw power and elegance. Surrounded by tall grass swaying gently in the breeze, the cheetah's every motion is captured in high definition, from the flex of its muscles to the gleam in its eyes, embodying the spirit of the wild in a captivating dance.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's body is twisted, its claws are twisted, its face is distorted, and its legs are twisted."
}
] |
seed46_1549
|
videos/HRA_part2/1549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, wearing a black t-shirt, blue jeans, and a silver wristwatch, stands against a plain gray backdrop. Initially, he looks intently at the camera, then breaks into a warm smile. Moments later, he playfully winks, showcasing his friendly demeanor. Finally, Jay is seen laughing wholeheartedly, his joyous spirit captured in high definition, all the while maintaining the simple outfit of a black top, blue denim, and a gleaming watch against the unadorned setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers were not generated, and the face was generated blurry."
}
] |
seed46_1107
|
videos/HRA_part2/1107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3148
|
videos/HRA_part1/3148.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. No obvious issues."
}
] |
seed46_1790
|
videos/HRA_part2/1790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars majestically over a vast body of water. Its piercing eyes scan the surface below for prey, its feathers ruffled by the wind. Suddenly, it dives headfirst into the water, emerging triumphantly with a wriggling fish clasped firmly in its talons. The osprey then flies off, heading towards its nest perched high in a tree, ready to feed its young. The scene is set against a backdrop of rolling hills and a clear blue sky, highlighting the bird's natural habitat and hunting prowess.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1026
|
videos/HRA_part1/1026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, donning a beige jacket, black t-shirt, and khaki pants, stands thoughtfully at a hot springs site, contemplating a unique shot. Suddenly, a rhinoceros emerges from the mist, leaping gracefully over a small pond within the springs. The director watches intently, camera in hand, ready to capture the extraordinary moment as the sun sets behind, casting a golden hue over the scene. The rhinoceros, now the central figure, jumps with surprising agility amidst the steamy waters, creating an unforgettable juxtaposition of nature and wildlife against the backdrop of the director's vision.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros suddenly flew into the director's hands."
}
] |
seed42_2542
|
videos/HRA_part0/2542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2266
|
videos/HRA_part1/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1931
|
videos/HRA_part0/1931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the children in the video are generated abnormally, with varying degrees of distortion and deformation in the middle frames."
}
] |
seed46_2435
|
videos/HRA_part2/2435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic stork, distinguished by its gray feathers and black wingtips, is captured in a series of poses. Initially, it stands tall on a grassy bank, legs firmly planted, looking alert. Then, it spreads its wings wide, ready for flight, with a serene lake and lush greenery serving as a backdrop. Next, the bird is seen in mid-flight, gracefully soaring over the water's surface, with its wings fully extended and head held high. Finally, it lands elegantly, tucking its wings and extending its long legs, touching down on the grass near the water's edge, completing the sequence of its daily activities by the lakeside.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1619
|
videos/HRA_part0/1619.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1024
|
videos/HRA_part1/1024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds as a farmer, clad in a traditional straw hat and plaid shirt, steers a futuristic tractor through a vast cornfield under a twilight sky filled with stars. The tractor, equipped with advanced technology and neon lights, glides smoothly over the soil, creating an otherworldly contrast against the rustic landscape. Suddenly, the farmer breaks into a joyful jig, dancing alongside his vehicle with a wide grin, celebrating the harvest under the celestial canopy. The sequence captures the unique blend of rural charm and space-age innovation, all set against the enchanting backdrop of a starlit night.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves are not smooth."
}
] |
seed42_1146
|
videos/HRA_part0/1146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a golden spacesuit, paints an antelope with vibrant colors under a starlit sky, with a spaceship gently docking in the background, casting a futuristic glow. The artist, now wearing a silver helmet and spacesuit, gracefully dances with the antelope, which has been transformed into a holographic projection, against the backdrop of a cosmic landscape filled with nebulae and distant galaxies. The scene shifts to reveal the artist inside the spaceship, where they continue to paint while floating in zero gravity, surrounded by their art supplies and the holographic antelope, which now moves in a synchronized dance, creating a mesmerizing display of art, technology, and movement in space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1976
|
videos/HRA_part0/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's crawling motion is discontinuous and undergoes sudden changes."
}
] |
seed46_1819
|
videos/HRA_part2/1819.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged teacher, wearing a gray jacket over a button-down shirt, shakes vigorously, appearing disoriented, with eyes closed and mouth agape, against a classroom backdrop featuring a whiteboard filled with algebraic equations. Moments later, she is seen in profile, shaking her head from side to side with eyes closed, suggesting intense emotion. Then, she shakes her head again, her expression reflecting determination, as she stands against a classroom wall adorned with a periodic table poster. Finally, she looks directly at the camera, shaking her head in disbelief, her demeanor and attire consistent throughout the scenes.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_321
|
videos/HRA_part0/321.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit sits quietly by a serene pond, the first light of sunrise on Mercury casting a pale, ethereal glow over the still waters. The sky is a deep shade of indigo, dotted with fading stars, while the distant horizon glimmers with the soft, alien light of the emerging sun. The rabbit, with its soft fur glistening with dew, prepares to take a unique plunge, as it gently enters the calm waters, creating ripples that expand across the glassy surface, under the enchanting, otherworldly beauty of a Mercury dawn.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit in the video was generated abnormally, and the overall content does not conform to reality."
}
] |
seed46_1359
|
videos/HRA_part2/1359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a gun holster, walks through a vast space library with high ceilings and large windows showing distant stars. The officer, with a serious yet calm demeanor, moves between towering bookshelves filled with ancient books and futuristic data pads. The library is illuminated by soft, ambient lighting, casting a warm glow on the officer's path. As they walk, the officer occasionally glances at the titles, perhaps searching for information or simply appreciating the knowledge stored within this unique cosmic repository.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2068
|
videos/HRA_part2/2068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, middle-aged with a neatly trimmed beard and glasses, prepares coffee in a break room. He measures coffee grounds into a filter with precision, ensuring the perfect cup. Wearing a gray shirt under a black vest and black pants, he pours water from a clear pitcher into the coffee maker with care. As the machine brews, he waits patiently, the steam rising from the freshly brewed coffee creating a warm, inviting atmosphere in the small space. He then pours the coffee into a white mug, the steam gently billowing upward, ready to enjoy a well-deserved break.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_210
|
videos/HRA_part0/210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, solitary rhinoceros is seen swimming in a natural body of water, surrounded by lush green vegetation. Its body is partially submerged, showing off its powerful swimming capabilities as it moves through the water. The rhino's head remains above the surface, its eyes focused ahead, and its mouth occasionally opening to breathe. The water gently laps at its thick skin, creating ripples that extend outward. In the background, tall trees and dense foliage provide a contrast to the open water where the rhinoceros swims.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3122
|
videos/HRA_part0/3122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brave firefighter, clad in full gear and a helmet, stands against the backdrop of a firetruck under a cloudy sky, waving confidently with his right hand. He wears a yellow reflective jacket over his equipment, adding a pop of color to the scene. In the next frame, he is seen from behind, still waving, with the red fire engine and a suburban neighborhood visible in the background. The firefighter then pauses his wave, looking intently at something off-camera, before continuing to wave amicably, his actions conveying reassurance and professionalism in the face of potential danger.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter can be clearly seen waving in the video, but the movements are not continuous and smooth, showing a lack of coordination."
}
] |
seed46_1417
|
videos/HRA_part2/1417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone buzzard soars gracefully across a vast, cloud-dappled sky, its wings spread wide in a display of effortless flight. Its keen eyes scan the rugged terrain below, a patchwork of sunlit earth tones and deep shadows cast by towering rock formations. The bird's majesty is further highlighted by its striking profile, showcasing its hooked beak and sharp talons as it circles overhead, a silent sentinel surveying its domain from the heavens. Against the dramatic backdrop of a sunlit landscape, the buzzard embodies the untamed spirit of nature in its purest form.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's wings and body generation in the video have issues."
}
] |
seed44_1348
|
videos/HRA_part1/1348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman stands tall in the middle of a crosswalk in a bustling city, clad in a long, camel-colored coat that reaches her knees, dark trousers, and high-heeled boots. Her outfit is complemented by a brown leather handbag hanging from her right shoulder. The cityscape behind her, featuring pedestrians, traffic lights, and urban architecture, adds to the dynamic setting. Her confident stance and the urban environment create a captivating scene, with the woman at the center, embodying poise and independence.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2346
|
videos/HRA_part1/2346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 plush koala toy, complete with realistic details and a charming face, comes to life against a green, leafy background reminiscent of eucalyptus. This adorable koala, clad in miniature jeans and a checkered shirt, begins to dance gracefully, its movements synchronized with an upbeat melody. Its paws sway side to side, and it gently bounces in place, capturing the essence of joy and playfulness. The dancing koala, set against the lush foliage, creates a delightful and enchanting moment, perfect for evoking smiles and happiness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2623
|
videos/HRA_part0/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's helmet and arm generation in the video have issues."
}
] |
seed46_1724
|
videos/HRA_part2/1724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A pristine, high-quality piece of cod fish is showcased, featuring a clean, white fillet with a compact, flaky texture. The fish is presented on a simple, rustic wooden board, accompanied by fresh lemon wedges and sprigs of dill, enhancing the natural freshness and flavor of the cod. The background is softly blurred, emphasizing the star of the show—the cod fish—while maintaining a clean, modern aesthetic. The lighting highlights the fish's texture and color, making it appear both appetizing and ready for culinary preparation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2814
|
videos/HRA_part0/2814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a royal blue scrubs top and light blue pants, stands against a white wall with a large, welcoming smile. She waves energetically with her right hand, her dark brown hair styled in a bun. Behind her, a row of lockers can be seen, adding context to the hospital setting. Her left arm rests by her side, and she wears a silver watch on her wrist. The nurse's eyes are closed as she waves, conveying genuine warmth and friendliness to the viewer.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's eyes in the video have generation issues, and the fingers are malformed."
}
] |
seed42_1884
|
videos/HRA_part0/1884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starship bridge, illuminated by soft blue and green lights, a small, fluffy white hare is crawling across the command deck. The hare moves slowly, its ears perked up, exploring the high-tech environment filled with control panels and large viewing screens displaying cosmic visuals. The bridge is otherwise empty, save for the advanced technology and the occasional blinking lights, creating a surreal contrast between the sci-fi setting and the unexpected presence of the crawling hare.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2265
|
videos/HRA_part0/2265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling mall filled with shoppers, a courageous firefighter clad in full gear, including a helmet and breathing apparatus, runs purposefully down a wide corridor. The vibrant red of his turnout coat contrasts sharply with the gray floor tiles and the bright storefronts. Escalators and elevators stand as silent witnesses to his urgent mission, while the clean, contemporary lines of the mall's architecture provide a stark backdrop to the unfolding drama. Amidst the commercial ambiance, the firefighter's presence and haste underscore the gravity of the situation, his figure growing smaller as he disappears into the distance, leaving behind a trail of determination and heroism.]"
},
{
"from": "gpt",
"value": "Normal. The person's hands, arms, and legs are distorted in the video."
}
] |
seed46_3216
|
videos/HRA_part2/3216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray jacket and blue jeans, runs with a determined look across a desolate industrial landscape dominated by oil refineries. The scene opens with him striding purposefully, his gaze fixed ahead. Next, he's seen mid-stride, his right arm extended forward, the refineries' towering structures and billowing smokestacks looming behind him. Then, he's captured in motion, his left foot lifting from the ground, the industrial backdrop providing a stark contrast to his vibrant attire. Finally, the artist continues his run, his silhouette framed against the imposing oil refinery complex, embodying resilience and movement in an urban-industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The artist's running motion in the video is not smooth."
}
] |
seed44_2752
|
videos/HRA_part1/2752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two small children wearing vibrant yellow raincoats and boots venture into a lush, green forest on a misty day. They walk side by side on a narrow dirt path, surrounded by towering trees and a dense undergrowth of ferns and moss. Suddenly, a curious red fox emerges from the foliage, its bright orange fur contrasting against the verdant backdrop. The fox pauses, looking directly at the children with intelligent eyes, as if sharing a silent moment of connection. The children, undeterred and full of wonder, continue their journey, leaving the fox to watch them from the safety of the woods, creating a heartwarming and enchanting moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2712
|
videos/HRA_part0/2712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heart of Tokyo, under the neon lights that bathe the bustling streets, a lone coyote wanders. Its golden eyes reflect the urban glow as it moves through the crowded alleyways. It pauses, the camera capturing a close-up of its face, showing the wild creature in an unexpected environment. The coyote then proceeds to wipe its face with a paw, a moment of natural behavior in stark contrast to the man-made surroundings. Behind it, the signs in Japanese and English, the busy storefronts, and the occasional passerby underscore the unlikely scene of a wild animal navigating the concrete jungle.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_112
|
videos/HRA_part0/112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of fresh mackerel fish, glistening under bright lights, showcases their vibrant silver scales, deep blue stripes, and dark spots. The fish lie on a bed of ice, their eyes clear and shiny, indicating peak freshness. The background features a bustling market scene, with vendors selling various seafood and customers browsing the selection. Focused on the mackerel, the camera captures every detail of the fish's texture and color, making them the star of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3016
|
videos/HRA_part2/3016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a khaki shirt and beige chinos, gently caresses a kangaroo in an Australian outback setting, surrounded by shrubbery and distant hills. The engineer, wearing safety goggles around his neck, interacts affectionately with the kangaroo, which stands on the ground, both under a clear blue sky. The kangaroo, with its distinctive marsupial pouch, is calmly accepting the engineer's touch, while the engineer's attire and demeanor suggest a blend of professionalism and compassion in this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's head appears deformed and malformed."
}
] |
seed46_2630
|
videos/HRA_part2/2630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show butter."
}
] |
seed44_1472
|
videos/HRA_part1/1472.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat and blue latex gloves, gently wipes a small, injured hedgehog with a cotton swab soaked in antiseptic solution, under the soft glow of an examination lamp. The hedgehog, nestled in a bed of green leaves, remains calm throughout the procedure, as the veterinarian carefully cleans its quills and skin. The scene is set in a cozy, well-lit clinic room filled with medical equipment and supplies, emphasizing the tender care provided to the tiny patient.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1439
|
videos/HRA_part1/1439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a small brown rat wearing swimming goggles and a red swim cap is seen floating in a pool, its limbs outstretched in a relaxed position. Behind it, the stunning rings of Saturn are visible, appearing as a backdrop in the night sky. The water is clear, reflecting the stars above, and the rat seems content in its unusual aquatic environment, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1377
|
videos/HRA_part0/1377.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a striking resemblance to Taylor Swift, known for her blonde hair and red lips, is seen in a series of scenes. First, she stands confidently against a backdrop of a gray wall, wearing a black leather jacket, a gray top, and black pants. Her stance suggests strength and determination. In the next scene, she walks away from the camera, showcasing her outfit and a casual, relaxed demeanor. Then, she is captured in a moment of laughter, leaning back, her smile wide and genuine, conveying a sense of joy and freedom. Lastly, she is seen mid-stride, walking purposefully towards the camera, her expression serious and focused, embodying the essence of the song 'Shake It Off' by Taylor Swift.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1093
|
videos/HRA_part1/1093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over casual attire, stands pensively on a pier overlooking a serene lake, the sky a blend of sunset orange and twilight blue. Moments later, he is seen in mid-air, having leaped from the pier, his arms spread wide in a joyful gesture. His lab coat flutters dramatically in the wind as he soars above the water, about to plunge into the lake's calm surface, the fading sunlight casting a golden glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The jumping action of the character in the video is very unsmooth."
}
] |
seed46_1589
|
videos/HRA_part2/1589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare, with its distinctive large ears and hind legs, is shown swimming across a clear, tranquil lake. It paddles with its front paws and kicks with its hind legs, using its ears to keep balance as it crosses the water. The hare's face, with its alert eyes and twitching nose, is visible above the waterline, and the background features lush green vegetation and a peaceful, overcast sky. The hare's fur, matted from the water, clings to its body, highlighting its muscular form as it swims purposefully toward the opposite shore.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2632
|
videos/HRA_part2/2632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, temperate shrubland during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's limbs are missing in the video, the ears are generated in the wrong position, the facial features are not generated, and the capybara appears quite late."
}
] |
seed44_2471
|
videos/HRA_part1/2471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a distinguished doctor, clad in a lab coat and stethoscope, runs alongside a prehistoric mammoth through an industrial landscape dotted with colossal power plants. Their breaths form visible clouds in the crisp air, as they navigate the terrain under an overcast sky. The mammoth's massive frame and the doctor's determined gaze create an unlikely alliance, their journey unfolding against the backdrop of towering smokestacks and power lines, blending elements of fantasy and reality in a captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the doctor's facial features and hands, as well as the head and limbs of the prehistoric mammoth, in the video has issues."
}
] |
seed42_15
|
videos/HRA_part0/15.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a young, bespectacled Asian male cashier, wearing a red apron over a gray shirt, stands in a dimly lit grocery store. Behind him hangs a large, vintage television playing footage of the historic moon landing. Suddenly, the focus changes to reveal a majestic deer walking calmly down the aisle, seemingly unfazed by its unusual surroundings. The cashier looks on in mild surprise, his expression a mix of bemusement and acceptance, as the deer continues its leisurely stroll among the shelves.]"
},
{
"from": "gpt",
"value": "Normal. The deer's movements are not smooth."
}
] |
seed46_2518
|
videos/HRA_part2/2518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a tranquil woodlands setting, characterized by lush vegetation and a serene atmosphere, a herd of majestic buffalo graze peacefully. The scene focuses on a single buffalo, its massive frame gently caressed by the soft branches of a weeping willow tree. The willow's slender leaves delicately brush against the buffalo's sturdy body, creating a tender and unexpected interaction between nature and wildlife. The buffalo's calm demeanor and the gentle sway of the willow branches in the breeze convey a sense of harmony and tranquility in the midst of the dense woodland.]"
},
{
"from": "gpt",
"value": "Normal. The bison's head in the video was generated abnormally."
}
] |
seed46_1289
|
videos/HRA_part2/1289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality close-up of a fresh cod fillet takes center stage, its surface glistening under bright lights. The fish boasts a clean, white flesh with a hint of natural oils visible, presenting a perfect texture for culinary delights. Set against a simple, dark background, the cod fillet's purity and freshness are accentuated, making it visually appealing for seafood connoisseurs and chefs alike.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1536
|
videos/HRA_part1/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's limbs in the video are poorly generated, the face is blurry, and the cow's limbs are defective."
}
] |
seed42_1011
|
videos/HRA_part0/1011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 film director, clad in a beige jacket, navy-blue shirt, and brown trousers, kneels on the floor of an art gallery, observing a taxidermied beaver. The setting is an exhibition space filled with various artworks, including paintings and sculptures. The director's intent gaze and body language suggest deep engagement with the beaver specimen, which is placed on a pedestal among other natural history exhibits. The camera captures this curious interaction from multiple angles, highlighting the director's fascination and the eclectic atmosphere of the gallery.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video has too many fingers generated."
}
] |
seed42_1769
|
videos/HRA_part0/1769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and dark pants, sprints with urgency across a wooden bridge overlooking a geyser's steamy plume in the background. The scene shifts to show the janitor running from right to left, with the geyser's eruption seen erupting behind him, emphasizing his hurried pace. Next, he is depicted dashing down a stone pathway, with the geyser's intermittent eruptions providing a dramatic backdrop. Finally, the janitor is shown sprinting on a dirt path, with the geyser's majestic plumes in the distance, highlighting his perseverance against the geothermal landscape.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1341
|
videos/HRA_part0/1341.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, exhibiting a powerful build with thick, dark fur and a muscular physique, runs across a lush, green savanna landscape under a bright, sunlit sky. The chimp's expressive face, featuring a wide mouth and intense eyes, conveys determination as it moves with agility and strength. Running in a hunched posture typical of its species, the chimpanzee demonstrates its natural locomotion, bounding over the terrain with a sense of purpose. The scene captures the essence of wild chimpanzees in motion, highlighting their dynamic physicality and the vibrant environment they inhabit.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's legs show signs of mutant deformity."
}
] |
seed42_1597
|
videos/HRA_part0/1597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted."
}
] |
seed44_1116
|
videos/HRA_part1/1116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a uniformed police officer kneels on lush green grass, gently caressing a tiny vole with utmost care and tenderness. The officer, wearing a classic navy blue police uniform with a badge and a cap placed nearby, ensures the small creature feels safe and secure. The vole, with its delicate features and curious eyes, seems at ease in the presence of the compassionate law enforcement figure. The background is a serene park setting, with trees and a clear blue sky, highlighting the unexpected yet touching connection between the officer and the vole.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements are not smooth."
}
] |
seed44_2808
|
videos/HRA_part1/2808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a black jacket and blue jeans, is seen caressing a kangaroo at a busy bus stop in the heart of a city. The scene opens with the actor standing next to the marsupial, both seemingly waiting for a bus amidst the urban landscape filled with pedestrians and traffic. As the camera focuses, the actor gently strokes the kangaroo's back, showing a tender connection between them. The kangaroo, unperturbed by the surroundings, leans into the touch, its eyes closed in apparent comfort. Behind them, the bustling city life continues, with cars passing by and people going about their day, creating a contrast to the intimate moment shared between the actor and the kangaroo.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1113
|
videos/HRA_part2/1113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1911
|
videos/HRA_part0/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the man petting the brown bear, but the movements are not smooth or coordinated; the brown bear's movements against the man are also not smooth or coordinated."
}
] |
seed46_1225
|
videos/HRA_part2/1225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda-costumed police officer sits in the cockpit of a futuristic space vehicle, navigating through the vast cosmos with a serious yet adorable demeanor. Moments later, the panda officer is shown swimming gracefully underwater, fully clad in the panda suit and police uniform, including a badge and a cap, creating a surreal and humorous contrast against the aquatic environment. The scene is set in a large, clear, space-themed aquarium, with stars and planets adorning the backdrop, merging elements of space travel and aquatic life in a playful and unexpected manner.]"
},
{
"from": "gpt",
"value": "Normal. The video fails to fully generate the panda's fingers and limbs in the underwater scenes."
}
] |
seed44_31
|
videos/HRA_part1/31.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, round and plump, navigates the vibrant coral reef with its intricate patterns and varied marine life, showcasing the wonders of the underwater world. Its body, inflated to twice its normal size, displays a mesmerizing display of geometric shapes in muted tones against the backdrop of the deep blue sea. The fish's small, beady eyes stand out prominently on its distended form, while its fins propel it gracefully through the water, surrounded by an array of colorful corals and other sea creatures. This underwater scene highlights the unique survival mechanism of the pufferfish in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1858
|
videos/HRA_part0/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The action of the student wiping the ritual face paint with fabric in the video is basically normal, but there is some inconsistency."
}
] |
seed44_1083
|
videos/HRA_part1/1083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant jungle setting, a group of intrepid explorers clad in khaki safari gear navigate a narrow, foliage-lined path, their expressions a mix of determination and awe. They pause momentarily, observing a majestic silverback gorilla ambling nearby, its powerful form moving gracefully through the underbrush. The gorilla, seemingly undisturbed by the presence of humans, continues its journey, highlighting the peaceful coexistence between wildlife and respectful visitors in this pristine natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The character's walking in the video is not smooth, and the movements are uncoordinated. The animal's movements are also uncoordinated."
}
] |
seed46_2203
|
videos/HRA_part2/2203.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic man named Jay, donning a gray blazer, black t-shirt, and jeans, stands in a dimly lit room with a warm color tone. Initially, he is seen in profile, gazing into the distance with a reflective look. Jay then turns to face the camera, his expression conveying a sense of determination and strength. Next, he smiles warmly, exuding confidence and approachability. Finally, Jay closes his eyes, appearing to savor a private moment of joy, all while the ambient lighting enhances the intimate atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed44_2204
|
videos/HRA_part1/2204.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-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 man's legs were not generated, and the man's hands appeared deformed and distorted."
}
] |
seed46_1620
|
videos/HRA_part2/1620.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 looking at the camera."
}
] |
seed46_2319
|
videos/HRA_part2/2319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed setting, a large, friendly capybara wearing a golden astronaut helmet embarks on a diplomatic mission. The capybara, donning a silver spacesuit and a golden astronaut helmet, crawls purposefully across a metallic space station floor, surrounded by high-tech equipment and screens displaying cosmic visuals. Its determined gaze and deliberate movements convey the importance of its interstellar diplomatic task. Nearby, alien delegates watch curiously, their various forms and colors contrasting with the capybara's brown fur and the sterile environment. The scene conveys a sense of unity and cooperation among different species in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed46_1403
|
videos/HRA_part2/1403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a grey hoodie, beige khakis, and brown boots, runs across a grassy field under a clear blue sky, holding a remote control. Nearby, a squirrel scampers along the ground, its bushy tail bouncing. In the distance, an AI-piloted drone hovers, capturing aerial footage. The engineer occasionally glances upwards, monitoring the drone's position as it flies, while the squirrel continues its journey among the trees. The scene is set in a suburban park, with houses visible in the background, highlighting the integration of technology and nature in everyday life.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel undergoes a mutation while running, with its body developing deformities."
}
] |
seed42_1352
|
videos/HRA_part0/1352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, resembling a young Russell Crowe, sits in a dimly lit room, deeply engrossed in sketching. He wears a white shirt with rolled-up sleeves, revealing a watch on his right wrist, and a black blazer draped casually over his shoulders. The room is adorned with various artworks, adding to the creative atmosphere. The actor's intense focus is evident as he draws, his face reflecting deep concentration. The camera captures his every move in stunning detail, from the way his fingers grip the pencil to the intensity in his eyes, all set against the backdrop of an art-filled room.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1832
|
videos/HRA_part1/1832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]"
},
{
"from": "gpt",
"value": "Bad. The cow was not generated in the video."
}
] |
seed44_140
|
videos/HRA_part1/140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Bad. The body movements are too strange, the actions are not continuous, and there are sudden changes. A chair in the hand suddenly disappears."
}
] |
seed46_1844
|
videos/HRA_part2/1844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's movements in the airport gift shop scene are basically normal, but the ferret's movements are not smooth; the ferret's movements in the pool scene are not smooth."
}
] |
seed44_137
|
videos/HRA_part1/137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]"
},
{
"from": "gpt",
"value": "Bad. The panda's movements are not smooth, and the character's movements are not smooth."
}
] |
seed46_3173
|
videos/HRA_part2/3173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, with a coat of dark fur and a muscular build, sprints across a lush, green savanna landscape, kicking up small clouds of dust with each stride. The chimp's powerful limbs propel it forward with agile determination, showcasing its natural athleticism in a vivid display of movement. As it runs, its eyes are fixed ahead, ears pressed back, and mouth slightly open, revealing a tongue panting from exertion. The background features tall grass swaying in the breeze and scattered acacia trees under a vast, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's running in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_2808
|
videos/HRA_part0/2808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a black jacket and blue jeans, is seen caressing a kangaroo at a busy bus stop in the heart of a city. The scene opens with the actor standing next to the marsupial, both seemingly waiting for a bus amidst the urban landscape filled with pedestrians and traffic. As the camera focuses, the actor gently strokes the kangaroo's back, showing a tender connection between them. The kangaroo, unperturbed by the surroundings, leans into the touch, its eyes closed in apparent comfort. Behind them, the bustling city life continues, with cars passing by and people going about their day, creating a contrast to the intimate moment shared between the actor and the kangaroo.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1362
|
videos/HRA_part0/1362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum after hours, a diligent worker in a blue uniform shirt crawls under an exhibit, focusing on maintenance tasks. The exhibit features ancient Egyptian artifacts, including a sarcophagus and hieroglyphic panels, with spotlights illuminating the space. The worker's attire includes safety gear, like gloves and a helmet, emphasizing the cautious approach required for handling historical items. The dimly lit museum hall, filled with glass display cases and statues, provides a dramatic setting for the solitary figure working beneath the exhibition platform.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a sarcophagus, hieroglyphics, glass display cases, or statues."
}
] |
seed42_2387
|
videos/HRA_part0/2387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vibrant yellow jacket and khaki shorts, walks along a dirt path near a watering hole, where a hippopotamus lazily wallows in the cool mud. In the distance, the Martian landscape unfolds, with its rusty red dunes and sparse vegetation silhouetted against a sunset painted in hues of violet and orange. The celestial event casts a warm glow over the scene, highlighting the unique juxtaposition of Earthly life and extraterrestrial beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2285
|
videos/HRA_part0/2285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a spacesuit adorned with patches and logos, embarks on a spacewalk to repair a satellite. She glides through the cosmos, the Earth visible in the distance, her movements methodical and confident. Her gloved hands, detailed with NASA symbols, work diligently on the intricate mechanisms, a tool kit secured to her waist. The vastness of space surrounds her, stars twinkling in the dark expanse, as she focuses on her task with the precision of her legal expertise. Throughout the sequence, her spacesuit helmet reflects the celestial backdrop, encapsulating the unique juxtaposition of her profession and this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video."
}
] |
seed44_261
|
videos/HRA_part1/261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2002
|
videos/HRA_part0/2002.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mallard duck floats placidly on the surface of a glassy lake, its vivid green head glistening in the sunlight, while its mottled brown back blends harmoniously with the natural surroundings. Nearby, cattails and reeds frame the serene scene, swaying gently in the breeze. The duck then proceeds to dip its head underwater, searching for food among the submerged plants, its body remaining visible above the waterline. As it surfaces, droplets of water scatter from its bill, capturing the tranquility and beauty of a day at the lake.]"
},
{
"from": "gpt",
"value": "Normal. The mallard's beak in the video is missing parts, and the eyes have not been generated."
}
] |
seed46_305
|
videos/HRA_part2/305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant zebrafish, distinguished by its alternating blue and gold stripes, swims gracefully in a clear, tranquil aquarium. The fish's fins, outlined in a darker hue, gently undulate as it navigates the water. In the background, a lush green plant provides a contrasting backdrop, highlighting the zebrafish's dynamic movements and coloration. Soft, ambient light illuminates the scene, casting delicate shadows and emphasizing the serene environment shared by the zebrafish and the verdant aquatic flora.]"
},
{
"from": "gpt",
"value": "Normal. The zebrafish fin generation position in the video is incorrect."
}
] |
seed44_2667
|
videos/HRA_part1/2667.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 musician, wearing a black jacket and blue jeans, gently caresses the head of a bison, which is lying down on a grassy field under a cloudy sky. The musician's left hand rests on the bison's snout, while the animal's eye is closed in apparent comfort. Both figures are set against a backdrop of green fields and distant mountains, with the bison's body partially obscured by the tall grass. The musician's right hand holds a harmonica, which hangs loosely by its strap, adding a musical element to the scene of connection between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The musician's left hand is not placed on the buffalo's nose, and the right hand holding the harmonica is not generated."
}
] |
seed44_1299
|
videos/HRA_part1/1299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unusual scene, a waiter wearing a black vest, white shirt, and black pants performs a kick in a dining room. The room features a long wooden table adorned with a white cloth, set with plates and glassware. The waiter's kick is high and assertive, contrasting with the formal setting. His black shoes, part of his uniform, add to the unexpected nature of the action. Behind him, a large window allows natural light to illuminate the space, highlighting the waiter's dynamic movement against the backdrop of the elegantly arranged dining area.]"
},
{
"from": "gpt",
"value": "Bad. The kick performed by the server in the video is not smooth and the movements are uncoordinated."
}
] |
seed46_2692
|
videos/HRA_part2/2692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warehouse district under a cloudy sky, a worker clad in a yellow vest and hard hat operates a compact yellow Bobcat excavator. The machine crawls carefully across the concrete floor, maneuvering through the tight spaces between towering stacks of pallets filled with cardboard boxes. The excavator's bucket is raised, ready to perform its task amidst the industrial environment, while the worker remains focused, guiding the machinery with precision.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2988
|
videos/HRA_part1/2988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1707
|
videos/HRA_part2/1707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, attired in a black jacket, gray turtleneck, and black pants, runs with urgency across a vast, barren lunar landscape, marked by craters and a horizon illuminated by Earth's distant glow. Carrying a small, symbolic urn, possibly containing ashes, the director's purposeful stride and determined facial expression convey a sense of mission. The scene is set against the backdrop of space, with stars twinkling in the dark expanse above, highlighting the solemnity and isolation of the act. The director's movement, juxtaposed against the stillness of the lunar surface, creates a dramatic tension, emphasizing the unique context of a 'space funeral' in motion.]"
},
{
"from": "gpt",
"value": "Bad. The director's face, hands, and legs in the video were generated incorrectly."
}
] |
seed42_1194
|
videos/HRA_part0/1194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his uniform consisting of a navy blue shirt with badges, dark pants, and black shoes, vacuums the carpet in a modest living room. The room features a small brown couch, a glass coffee table, and a beige recliner, with sunlight streaming through the window, highlighting dust particles in the air. The officer, displaying a serious demeanor, methodically maneuvers the vacuum cleaner across the carpeted floor, revealing his commitment to household chores despite his profession. The domestic scene contrasts sharply with his authoritative attire, emphasizing the duality of his role as both protector and provider.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2811
|
videos/HRA_part0/2811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a traditional conical hat and simple clothing, guides a strong water buffalo through a shallow, muddy waterway by holding onto its rope halter. The buffalo, with its large, curved horns and powerful body, crawls on its belly through the mire, demonstrating its strength and endurance. The farmer, with a focused look on his face, carefully navigates alongside the animal, highlighting the bond between man and beast in rural life. The scene takes place against the backdrop of lush green fields, emphasizing the agricultural setting.]"
},
{
"from": "gpt",
"value": "Bad. The horns of the water buffalo in the video have generation issues, and the eyes and tail are generated unnaturally."
}
] |
seed46_2209
|
videos/HRA_part2/2209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1617
|
videos/HRA_part0/1617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a white lab coat over a gray t-shirt and khaki pants, stands in a futuristic, metallic laboratory. Holding a high-tech device, he demonstrates the concept of time dilation, with visual effects distorting the background and a digital clock appearing to slow down. The scene progresses as he uses a cloth to wipe the perspiration from his forehead, emphasizing the intensity and complexity of his scientific endeavor. Throughout, the lab's modern aesthetic and advanced technology underscore the theme of cutting-edge research and experimentation.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the character in the video are not smooth and continuous."
}
] |
seed46_1158
|
videos/HRA_part2/1158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant village nestled near a lush watering hole, a tall giraffe gracefully bends its neck to drink, its spots blending harmoniously with the African landscape. Nearby, village life unfolds, with women carrying water pots on their heads, children playing under the watchful gaze of elders, and men engaged in lively conversations. Suddenly, a group of young boys leap into the refreshing waters, their joyful splashes contrasting with the calm surroundings. The scene is completed by a close-up of a giraffe's face, its large eyes and curious expression capturing the essence of this serene environment.]"
},
{
"from": "gpt",
"value": "Normal. No scene of a group of young boys jumping into the water to play."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.