video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1850
|
videos/HRA_part0/1850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful cashier, wearing a green apron over a casual outfit, stands in a pet store, carefully washing a small brown dog in a white tub. The dog, on a leash, looks relaxed and happy, sitting in soapy water while the cashier, sporting a stylish bun hairstyle, uses a handheld showerhead to rinse the suds away. The scene is set against a backdrop of pet supplies and products, creating a vibrant and welcoming environment. The cashier's warm smile and gentle touch convey a sense of care and affection for the animal, making it a heartwarming moment captured on video.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's action of petting the dog in the video is basically normal, with only slight awkwardness."
}
] |
seed42_2549
|
videos/HRA_part0/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3123
|
videos/HRA_part0/3123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dimly lit warehouse complex, a renowned film director, wearing a black leather jacket, gray shirt, and jeans, kneels among stacks of wooden crates. With a handheld camera, he captures footage of a giant panda cub crawling across the dusty floor, its fluffy black and white fur contrasting with the industrial setting. The panda moves slowly, exploring its surroundings with curiosity, while the director films intently, capturing every detail of this unusual encounter in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, the hands are twisted, the panda's body is deformed, and the legs are twisted."
}
] |
seed46_1296
|
videos/HRA_part2/1296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female worker sits on a wooden chair under the shade of a tree, knitting a long, colorful scarf with red, green, and yellow yarns. She wears a simple cotton dress and sandals, her hair tied back in a bun. The scene is set in a small courtyard surrounded by lush greenery and blooming flowers, with sunlight filtering through the leaves, casting dappled shadows on the ground. The woman's hands move deftly, the knitting needles clicking together in a steady rhythm, as she focuses intently on her work, occasionally glancing up to enjoy the peaceful surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The woman knitting in the video is not smooth and her movements are uncoordinated."
}
] |
seed44_1924
|
videos/HRA_part1/1924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic room filled with advanced technology and screens displaying alien landscapes, a renowned director, dressed in a black turtleneck and jeans, sits in a swivel chair, intently observing a large screen. Suddenly, an otherworldly creature, resembling a cross between a mouse and an alien, emerges from the shadows. With a look of wonder and curiosity, the director gently extends a hand, initiating a tender caress of the creature's soft fur, highlighting a peaceful and unexpected interspecies connection. The scene is framed by high-definition visuals and enhanced by the ambient glow of the tech-filled environment, emphasizing the director's calm and respectful interaction with the unique being.]"
},
{
"from": "gpt",
"value": "Normal. The director's movements while touching the mysterious creature in the video are not smooth and coordinated."
}
] |
seed46_1428
|
videos/HRA_part2/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2344
|
videos/HRA_part1/2344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1787
|
videos/HRA_part1/1787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a brown vest and khaki trousers, races through lush, green vineyards, his expression one of determination. He is followed closely by a prehistoric mammoth, its massive body and shaggy fur moving surprisingly swiftly through the rows of grapevines. The sun, low in the sky, casts long shadows across the fertile landscape, highlighting the unusual pair as they navigate the terraced fields. In the background, a rustic barn and rolling hills provide a classic countryside setting, contrasting with the extraordinary sight of the farmer and the mammoth in motion.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3208
|
videos/HRA_part1/3208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a red neckerchief and a brown apron, stands in a modern kitchen. He holds a large, open recipe book in his hands and writes with a silver pen, his face expressing deep concentration. The kitchen is filled with stainless steel appliances and shelves stocked with various cooking ingredients, creating a professional culinary atmosphere. The chef's sleeves are rolled up, revealing a watch on his wrist, and he occasionally glances up from the book, likely checking the progress of dishes being prepared in the bustling kitchen environment.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand and the silver pen are deformed."
}
] |
seed46_199
|
videos/HRA_part2/199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's arm is deformed and elongated, and the hand appears deformed."
}
] |
seed42_1856
|
videos/HRA_part0/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. The head and hand of the girl jumping beside the otter enclosure in the zoo are generated incorrectly; when at the cemetery, the girl's hands and feet are generated twisted and deformed."
}
] |
seed46_2286
|
videos/HRA_part2/2286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black beret and glasses, is seen in a studio filled with vibrant paintings and art supplies. He exhibits a range of emotions, from frustration to determination, as he shakes his head vigorously. Against the backdrop of a vividly painted wall, the artist's movements are exaggerated, emphasizing his passionate engagement with his craft. His expressive face and animated gestures convey the intensity of his creative process, offering a glimpse into the emotional rollercoaster of artistic expression.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed44_1169
|
videos/HRA_part1/1169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron, with its signature blue-gray feathers and long, slender legs, stands majestically in the shallow waters of a serene lake. Its sharp, yellow eyes scan the water's surface as it patiently awaits its next meal. Suddenly, the heron strikes with lightning speed, its sharp beak piercing the water to catch a small fish. As it emerges victorious, the heron proudly displays its catch before swallowing it whole. All the while, the calm surroundings of the lake provide a peaceful backdrop, with gentle ripples on the water and the distant silhouette of trees completing the scene.]"
},
{
"from": "gpt",
"value": "Bad. No generation of small fish, heron's beak is not sharp, yellow eyes is not generated."
}
] |
seed42_1892
|
videos/HRA_part0/1892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier, donning a red apron with a name tag, works diligently behind a cluttered grocery store checkout counter. She is in the process of changing the batteries in a barcode scanner, handling the device with care and precision. The scene is set in a bustling supermarket, with customers waiting patiently in line, and the cashier's actions are framed by shelves stocked with various products. As she replaces the batteries, her focused expression conveys her commitment to ensuring the scanner functions smoothly, maintaining the efficiency of the checkout process.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the female cashier replacing the barcode scanner battery in the video are not smooth and continuous, with abrupt changes."
}
] |
seed46_2985
|
videos/HRA_part2/2985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist with a shaved head and wearing a gray shirt is seen organizing items on metal shelves against a gray backdrop. Initially, he is placing objects with care, showcasing his meticulous nature. Moments later, he is shown adjusting the arrangement of items, revealing his attention to detail. Then, he is seen moving an object to another shelf, indicating his methodical approach to organization. Finally, he looks satisfied with his efforts, his posture and facial expression reflecting a sense of accomplishment, all within the minimalist setting of a gray room with metal shelving units.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm undergo deformation and mutation, and in the end, the entire body deforms and shrinks."
}
] |
seed42_2416
|
videos/HRA_part0/2416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon is presented on a plate, its skin crispy and charred to perfection, the flesh a rich pink hue that contrasts strikingly with the green of the accompanying asparagus spears. The dish is garnished with lemon wedges and fresh dill, enhancing the vibrant colors and textures. The salmon is shown from multiple angles, revealing its succulent interior and the delicate grill marks that add depth and character to the presentation. Set against a rustic wooden table, the scene is completed by a glass of white wine and a simple white bowl containing a side of creamy mashed potatoes, offering a perfect balance of flavors and visual appeal.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_288
|
videos/HRA_part0/288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short, brown hair and glasses, wearing a patterned, blue medical scrub top and black pants, hangs framed pictures on the walls of a brightly lit hospital room. She stands on a small, yellow stool to reach the wall above a patient's bed, where a colorful, abstract artwork is already hung. The nurse carefully aligns a new frame next to it, creating a comforting environment for patients. She uses a level to ensure each piece is straight, revealing her attention to detail in the cozy, well-decorated space. Throughout, she maintains a warm smile, demonstrating her caring nature as she enhances the room's aesthetic with more framed prints.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are slightly unsmooth."
}
] |
seed44_3087
|
videos/HRA_part1/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1301
|
videos/HRA_part1/1301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of four young children, two boys and two girls, are joyfully splashing in a clear blue swimming pool, their laughter echoing in the bright, sunny day. One boy, wearing green swim trunks, playfully jumps into the water from the side of the pool, creating a splash. Meanwhile, a small, curious brown mouse peers over the edge of the pool, its tiny head poking out, seemingly intrigued by the commotion and the splashing water. The children, unaware of the mouse's presence, continue to swim and play, their faces full of delight and energy, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is twisted, the mouse's body is twisted, and the claws are twisted."
}
] |
seed44_2745
|
videos/HRA_part1/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed44_300
|
videos/HRA_part1/300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown horse gallops across a lush, green meadow under a clear blue sky, its muscular body rippling with each powerful stride. The horse's mane and tail flow dramatically in the wind, creating a sense of speed and freedom. A pair of vibrant yellow flowers appear briefly in the foreground, adding a pop of color to the scene. The horse continues its run, hooves kicking up small clumps of earth, highlighting its strength and grace as it moves through the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 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, 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 chimpanzee's running motion in the video is not smooth and continuous, there are abrupt changes."
}
] |
seed42_2021
|
videos/HRA_part0/2021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 standard uniform with a badge, hat, and tactical vest, stands under a dimly lit streetlamp on a quiet, empty urban street at night. The officer's face is contorted in anguish, tears streaming down their cheeks, highlighting the emotional weight they carry. Their eyes are closed, and they're holding a tissue in one hand, indicating a moment of vulnerability amidst their duty. The scene conveys a powerful message about the human side of law enforcement, emphasizing the emotional toll it can take on those who serve.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and the hand appears deformed."
}
] |
seed46_1221
|
videos/HRA_part2/1221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magpie perches on a branch, its glossy black and white feathers shimmering under the sunlight, showcasing the bird's striking plumage against a lush green forest backdrop. The magpie turns its head, revealing its intelligent eyes and sharp beak, highlighting its curious nature. Moments later, it spreads its wings, displaying the full span of its black and white feathers, before taking flight, leaving behind a flurry of feathers and a sense of awe at its beauty and grace. Throughout the scene, the magpie remains the central focus, captivating the viewer with its natural elegance and charm.]"
},
{
"from": "gpt",
"value": "Normal. The magpie's flying movements in the video are not coordinated."
}
] |
seed44_2342
|
videos/HRA_part1/2342.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman, dressed in a form-fitting black outfit, moves in sync with a sleek black panther, both crawling across a barren, rocky terrain under a dusky sky. Their synchronized movements and intense eye contact suggest a powerful connection, as they navigate the rugged landscape together. The woman's attire mirrors the panther's fur, creating a striking visual harmony against the stark, natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand and the black panther's claws are generated abnormally, with sudden distortions appearing in the middle frames."
}
] |
seed42_1732
|
videos/HRA_part0/1732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, wide flounder fish is seen lying motionless on a clean, white surface, its right eye gazing upwards, while the left side of its body, which lacks an eye, is pressed against the surface. The fish has a natural sandy-brown color with darker mottled spots, giving it a realistic appearance. Its texture is depicted with fine, realistic details, emphasizing the flatness and unique form of the flounder species. The setting is minimalistic, focusing solely on the fish against the pristine white background, allowing for a clear and unobstructed view of the subject.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2461
|
videos/HRA_part0/2461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, dressed in a white lab coat, is seen on the ground, crawling on hands and knees as if examining something closely. Beside him, a giraffe, curious and gentle, bends its long neck to look down at the situation, its eyes filled with intrigue. The setting is a vivid green savanna, with tall grass swaying in the breeze and distant acacia trees dotting the horizon, creating a surreal juxtaposition of medical professionalism and the wild nature of Africa.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2173
|
videos/HRA_part0/2173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2050
|
videos/HRA_part1/2050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a futuristic silver jacket and dark pants, races across the barren, rocky terrain of Mars under a stunning night sky filled with stars and two moons. The landscape features red soil and distant Martian mountains, with the Milky Way galaxy prominently visible above. The writer pauses mid-stride, gazing upwards in awe and inspiration, before continuing the run with determination, the dynamic scene capturing the essence of stargazing from the Red Planet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1615
|
videos/HRA_part0/1615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, dressed in a sky-blue scrubs top and matching cap, tends to a patient in an expansive, sunlit grassland. She gently wipes the patient's face with a soft cloth, her caring demeanor evident in her focused eyes and gentle smile. The serene landscape of tall, swaying grass and distant, rolling hills provides a peaceful backdrop to the intimate moment of care. The nurse's attire, emblematic of her profession, contrasts beautifully with the lush greenery, highlighting her role as a caregiver in this unexpected outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's actions in the video of using a soft cloth to wipe the patient are basically normal, with only slight awkwardness."
}
] |
seed44_2813
|
videos/HRA_part1/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, stands next to a large, brown buffalo with a red saddle. The officer gently wipes the buffalo's face with a white cloth, showing care and attention. The scene takes place in a rural setting, with wooden fences and green fields stretching into the distance. The buffalo, with its massive horns and calm demeanor, contrasts with the authoritative presence of the police officer, creating an unusual yet harmonious image.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1544
|
videos/HRA_part1/1544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a brown uniform, diligently wipes the glass enclosure of a wildlife exhibit, where a graceful gazelle is seen resting calmly inside. The enclosure is meticulously clean, save for a few lingering spots that the worker is addressing. The gazelle, displaying a relaxed demeanor, is positioned near the enclosure's entrance, its body language indicating a sense of security and comfort within its habitat. The scene captures the routine maintenance of the animal's living space, highlighting the careful interaction between the human caretaker and the wild creature in a shared environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2792
|
videos/HRA_part1/2792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two young boys, one in a red bathing suit and the other in a green one, splash playfully in a backyard pool on a sunny day. Suddenly, the focus is on the boy in red, who is seen diving into the clear water. A small, friendly rat, perhaps a pet, watches from the side of the pool, its tiny body perched on the edge as it observes the boys' aquatic fun. The scene exudes joy and innocence, with the rat's presence adding a touch of unexpected charm to the children's summertime activities.]"
},
{
"from": "gpt",
"value": "Good. Basically no problems."
}
] |
seed46_2891
|
videos/HRA_part2/2891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 miniature giraffe, no taller than a foot, crawls slowly across the surface of a vast, cosmic solar sail, its fabric shimmering with ethereal light against the backdrop of a star-studded universe. The giraffe, with its distinctive pattern and gentle demeanor, moves deliberately, exploring the alien landscape as if it were a terrestrial savanna. The sail, stretched taut and capturing the rays of a distant sun, provides a mesmerizing contrast to the earthly creature traversing its surface, creating a dreamlike juxtaposition between the terrestrial and the celestial.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's walking movements in the video are uncoordinated."
}
] |
seed44_1349
|
videos/HRA_part1/1349.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed figure, dressed in a full-body brown bear suit, performs a lively jig atop a lush, green heathland blanketed with purple heather flowers. The dancer's movements are energetic and joyful, their bear-clad form spinning and leaping against the vibrant landscape. The heathland stretches out behind them, dotted with patches of colorful blooms and tall grasses swaying in the breeze. The sky above is a brilliant blue, with wispy clouds adding texture to the horizon. Throughout the scene, the dancing bear remains the central focus, their animated presence captivating against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2290
|
videos/HRA_part1/2290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and gray sweatpants, diligently wipes down a large, brown bison statue with a white cloth, showing care and attention to detail. The scene takes place on a grassy campus, with trees in the background, highlighting the unique connection between the student and the symbolic animal figure. The student's focused expression and the careful motion of wiping the bison's surface convey a sense of respect and tradition associated with university life.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the student wiping the buffalo statue, the action is basically normal but there is some lack of coordination."
}
] |
seed46_1421
|
videos/HRA_part2/1421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, wearing a red checkered shirt, brown apron, and khaki pants, takes a break from cooking to rake leaves in a suburban backyard. He pauses for a moment, looking thoughtful, before continuing his task with determination. The chef, now smiling, rakes a large pile of autumn leaves into a heap, enjoying the crisp fall weather. Finally, he pauses again, this time looking pleased with his work, standing next to the sizable leaf pile, with his rake resting on his right shoulder, and a residential neighborhood visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and fingers are not fully generated, and the rake deforms during the process of raking leaves."
}
] |
seed42_2632
|
videos/HRA_part0/2632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, temperate shrubland during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's head and limbs in the video have generation issues, with its limbs suddenly disappearing or appearing in the middle frames."
}
] |
seed44_3200
|
videos/HRA_part1/3200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Normal. The jackal's jumping action in the video is slightly unsmooth."
}
] |
seed44_1879
|
videos/HRA_part1/1879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding teacher sits slumped at a large wooden desk, surrounded by stacks of books and papers, in a dimly lit room. His glasses have slipped down his nose, and his head rests on a pile of graded exams, indicating exhaustion from late-night grading. The cluttered desk, filled with educational materials, suggests a dedicated educator overwhelmed by his workload. Behind him, a window reveals the glow of streetlights outside, hinting at the late hour. The teacher's weary posture and closed eyes depict a moment of much-needed rest amidst the demands of his profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3213
|
videos/HRA_part2/3213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The server's face and hands are distorted in the video."
}
] |
seed44_1478
|
videos/HRA_part1/1478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing her uniform consisting of a white collared shirt, black pants, and a name badge, takes a break from her duties to clean the gutters of the medical facility. She stands on a ladder, her gloved hands scooping out debris, with the sunny day highlighting her dedication beyond her regular responsibilities. The video showcases her multitasking abilities, as she balances her healthcare role with the practical needs of maintaining the clinic's infrastructure, all while dressed in her recognizable nursing attire.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1212
|
videos/HRA_part1/1212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic wild salmon, exhibiting vibrant hues of silver, red, and green, swims gracefully in a crystal-clear river, its scales shimmering under the natural sunlight filtering through the water. The salmon's powerful body and forked tail are showcased as it propels itself upstream against the current, highlighting its determination and strength in nature's challenging environment.]"
},
{
"from": "gpt",
"value": "Bad. The fish is above the water surface, which is not realistic."
}
] |
seed42_1623
|
videos/HRA_part0/1623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, likely his cub, against the backdrop of a lush, green savannah during the golden hour. The father lion, with his thick, dark mane, displays affection and protection as he rubs his cheek against the cub's head. The cub, with its curious eyes and playful demeanor, responds with a nuzzle of its own, showcasing the intimate bond between them. This heartwarming interaction unfolds under a sky painted with warm hues of orange and pink, highlighting the emotional connection between the two lions.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1462
|
videos/HRA_part1/1462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The officer's actions of feeding the cat in the video are not continuous and there are abrupt changes."
}
] |
seed42_1620
|
videos/HRA_part0/1620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 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 human hand appears to have undergone a deformity mutation."
}
] |
seed42_1831
|
videos/HRA_part0/1831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, wearing a white lab coat and blue gloves, is seen wiping the nose of a friendly coyote who is sitting calmly on a checkered medical table. The room is brightly lit, with medical supplies neatly arranged on shelves in the background. The doctor's compassionate expression and the coyote's trusting demeanor create a heartwarming moment, highlighting an unusual yet tender interaction between human and wild animal in a clinical setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2526
|
videos/HRA_part1/2526.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giraffe, distinguished by its dark, jagged spots, gently caresses a smaller giraffe with its head, creating a tender moment in the midst of a lush, green savanna landscape. The taller giraffe, with a weathered face and long eyelashes, shows affection toward the younger one, which has lighter, less pronounced markings, standing against a backdrop of tall grasses and distant trees under a bright, sunny sky. This intimate scene captures the essence of giraffe behavior in their natural habitat, emphasizing the bond between two individuals against a vivid, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2757
|
videos/HRA_part1/2757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cartoon style, a cheerful nurse with rosy cheeks, bright eyes, and a traditional uniform is depicted mid-jump, with a small, friendly rat leaping alongside her. Both the nurse and the rat display exaggerated expressions of joy and excitement, capturing a sense of playful camaraderie. The nurse's outfit is crisp and clean, adding to the overall upbeat and carefree atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's jumping action in the video is basically normal, with slight disharmony."
}
] |
seed46_2516
|
videos/HRA_part2/2516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sequence, a lone firefighter, clad in full gear and helmet, is engaged in an interpretive dance within a vast, subtropical desert landscape. The horizon showcases a blend of orange and purple hues, reminiscent of a dramatic sunset. Suddenly, a majestic bison emerges from the distant dunes, its silhouette outlined against the fading light. It watches the dancing firefighter with a curious gaze, as if understanding the emotive performance unfolding before it in the midst of the arid, desolate environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1404
|
videos/HRA_part1/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Bad. The bat did not appear in the video."
}
] |
seed44_3149
|
videos/HRA_part1/3149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 animated scene, a small, adventurous mouse dons a director's cap and carries a clapperboard, energetically guiding the action within a vibrant space casino. The setting is filled with neon lights, futuristic slot machines, and alien creatures gambling. Our rodent director, wearing a tiny suit and tie, races through the bustling casino floor, dodging patrons and games of chance, all while maintaining control over the film production taking place in this extraordinary intergalactic entertainment hub.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2981
|
videos/HRA_part0/2981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cheerful cashier, donning a green apron and a nametag, is playfully dancing with a friendly horse inside a vibrant, cartoonish grocery store. The cashier, with short brown hair and a wide smile, leads the horse in a lively jig down the aisles, filled with brightly colored products. The horse, adorned with a polka-dotted bowtie and a pair of oversized sunglasses, happily trots alongside, its hooves gently tapping the checkered floor. Shoppers look on in amused surprise, some pausing to capture the unexpected spectacle on their phones, while others continue browsing the shelves, seemingly unfazed by the unusual dance party unfolding before them.]"
},
{
"from": "gpt",
"value": "Normal. The cashier and the horse can be clearly seen dancing in the video, the movements are basically normal but there is some lack of coordination."
}
] |
seed44_22
|
videos/HRA_part1/22.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, bundled in a heavy coat, mittens, and a woolen cap, stands beside a friendly moose in a quaint village setting marked by wooden houses and snow-covered landscapes. The student gently wipes snowflakes from the moose's antlers, both gazing into the camera with a sense of camaraderie. Behind them, smoke rises from chimneys, indicating the warmth of homes in the cold environment. The scene is set during the golden hour, with soft, warm light casting long shadows across the snow, creating a cozy and welcoming atmosphere in the village.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1580
|
videos/HRA_part0/1580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a yellow safety vest over a gray shirt, blue jeans, and brown shoes, climbs a tall, metal, industrial ladder in a large warehouse filled with boxes and equipment. He holds a tool in his right hand and reaches up with his left, the afternoon sun shining through the high windows, casting a warm glow over the dusty space. The ladder leans against a tall shelf stacked with supplies, and the man's focus is intense as he ascends, his brows furrowed in determination. Behind him, the vastness of the warehouse stretches out, with rows of shelves disappearing into the distance, emphasizing the scale of his task.]"
},
{
"from": "gpt",
"value": "Normal. There are issues with the generation of the character's limbs."
}
] |
seed46_1598
|
videos/HRA_part2/1598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A thoughtful male writer, wearing a blue jacket, dark jeans, and brown shoes, walks through dense shrubbery in a thick forest during daytime. His hands are tucked into his pockets as he strolls, appearing lost in thought. He pauses to observe his surroundings, which include lush green foliage and towering trees. Continuing his journey, he strides confidently, navigating the uneven terrain formed by rocks and tree roots. Throughout the scene, the writer maintains a contemplative demeanor, suggesting a creative mind at work amidst the natural beauty of the woodland environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1224
|
videos/HRA_part0/1224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue uniform and a stethoscope around her neck, is delightedly interacting with a small gerbil in a cozy living room. The gerbil, perched on a tiny platform, suddenly leaps into the air, its action frozen in mid-jump, capturing a moment of playful exuberance. The nurse, with a warm smile, watches the gerbil's antics, her caring demeanor evident in her facial expression and body language. The scene is set against a backdrop of a homely living space, with a couch, coffee table, and various household items visible in the background, creating a sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1475
|
videos/HRA_part1/1475.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a yellow shirt and black leggings stands before a large aquarium filled with exotic fish, carefully cleaning the glass with a magnetic cleaner in her right hand. The fish swim curiously around the algae-covered areas she has yet to clean, while the bubbles from her cleaning tool ascend gently. The room is softly lit, casting a warm glow on the woman's focused face as she leans into her task. Behind her, a window lets in natural light, illuminating the space and highlighting the water droplets on the outside pane. Throughout, she remains engrossed in her work, ensuring each section of the tank is spotless.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arm in the video is poorly generated, and her fingers are missing."
}
] |
seed46_1124
|
videos/HRA_part2/1124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a dark green shirt and khaki pants, checks smoke detectors in a dimly lit office hallway. He is seen standing on a red ladder, holding a tool, with his focus entirely on the detector. Moments later, he is shown descending the ladder, with a slight smile and a nod, indicating his satisfaction with the detector's condition. He carries a black tool bag and wears a name badge, adding to his professional appearance. The video ends with him walking down the hallway, checking another smoke detector, maintaining safety in the workplace.]"
},
{
"from": "gpt",
"value": "Bad. The person's legs are deformed and the black bag appears suddenly. The person on the ladder does not have feet generated. The red ladder disappears suddenly. The person's face is deformed."
}
] |
seed42_1348
|
videos/HRA_part0/1348.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stylish woman 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."
}
] |
seed42_2441
|
videos/HRA_part0/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 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 well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the monkey's movements are also not smooth."
}
] |
seed46_1987
|
videos/HRA_part2/1987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young male cashier, dressed in a gray shirt and wearing glasses, is attentively listening with a slight smile, his head tilted to one side. He stands behind a clean, organized supermarket counter, with a large, clear space in front of him. The scene is set during the day, with good lighting from overhead lights. Beside him, a female customer, wearing a brown jacket and a colorful scarf, speaks to him, her mouth open as she engages in conversation. The setting is a modern grocery store, with shelves of products visible in the background, and the atmosphere is calm and pleasant.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1455
|
videos/HRA_part0/1455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a white apron over a blue checkered shirt and khaki pants, abandons his culinary pursuits to embrace a different kind of artistry. Holding a paintbrush in his right hand, he applies vibrant red paint to a wall, creating an abstract design reminiscent of a Jackson Pollock masterpiece. The room, with its white walls and wooden floorboards, serves as a blank canvas for his newfound passion. As he works, his concentration is palpable, revealing a side of him that finds fulfillment beyond the kitchen. The transformation of the space from a simple dining area into a colorful, artistic haven underscores his creative versatility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1831
|
videos/HRA_part1/1831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, wearing a white lab coat and blue gloves, is seen wiping the nose of a friendly coyote who is sitting calmly on a checkered medical table. The room is brightly lit, with medical supplies neatly arranged on shelves in the background. The doctor's compassionate expression and the coyote's trusting demeanor create a heartwarming moment, highlighting an unusual yet tender interaction between human and wild animal in a clinical setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2753
|
videos/HRA_part2/2753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stark juxtaposition, a majestic brown horse gallops across a lush green meadow under a vibrant blue sky speckled with white clouds, the rolling hills framing the scene beautifully. Meanwhile, in the distance, smokestacks from sprawling factories loom, emitting plumes of gray smoke into the air. On the ground near the horse, a small creature crawls, its perspective offering a unique view of the vast landscape, highlighting the contrast between nature's grace and industrial might.]"
},
{
"from": "gpt",
"value": "Bad. The horse's head and limbs in the video have generation issues, with the horse having five legs in some middle frames, and the video overall does not conform to reality."
}
] |
seed46_1575
|
videos/HRA_part2/1575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker in a lab coat walks purposefully across a large, open laboratory space filled with complex machinery and high-tech equipment, the setting for a quantum entanglement experiment. The room is illuminated by bright overhead lights, casting a sterile glow over everything. In the background, scientists can be seen observing data on computer screens and discussing theories, their faces serious and focused. The worker carries a clipboard, pausing occasionally to check notes or adjust settings on various machines, all while surrounded by the hum of active scientific inquiry into the mysteries of quantum mechanics.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1423
|
videos/HRA_part2/1423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray sweater and glasses, sits at a rustic wooden desk in a cozy room filled with books, typing away on a vintage typewriter. Beside her, a curious ferret emerges from a cage, its bright eyes scanning the environment. The animal then embarks on a playful walk across the desk, exploring various objects like a small potted plant and a glass jar. Throughout the scene, the writer continues to type, occasionally glancing at the ferret with a smile, capturing the essence of a peaceful day in her life, surrounded by literary works and a charming pet.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are not smooth."
}
] |
seed44_2035
|
videos/HRA_part1/2035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2822
|
videos/HRA_part0/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Ba. The foot generation is uneven."
}
] |
seed46_2189
|
videos/HRA_part2/2189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a sleek black panther, adorned with a red bow tie, calmly walks down a brightly lit supermarket aisle filled with neatly arranged products. The panther gently wipes its paw across the shelves, leaving a trail of sparkling cleanliness. The shelves are stocked with various goods, from canned foods to household items, all bathed in a warm, inviting glow. The panther continues its meticulous cleaning, moving gracefully through the aisles, as if it were a routine task in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and tail of the black panther in the video are missing, and the bow tie is not fully generated."
}
] |
seed44_3209
|
videos/HRA_part1/3209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man and kangaroo's running movements are not smooth."
}
] |
seed46_1587
|
videos/HRA_part2/1587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of a grouse's head showcases its distinctive red facial wattles and curious, alert expression, set against a blurred forest background. The bird's intricate feather patterns are highlighted, particularly the dark speckles on its brownish-grey plumage. Its sharp, intelligent eyes and slightly open beak convey a sense of awareness and readiness in its woodland habitat. The grouse is perched on a branch, surrounded by lush greenery, with rays of sunlight filtering through the leaves, illuminating its feathers and the rugged bark of the tree.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_113
|
videos/HRA_part2/113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker in a power plant environment is seen wiping down a large turbine with a yellow cloth, dressed in a navy blue uniform, complete with a shirt, trousers, and safety shoes. The scene captures the maintenance aspect of power generation, with the worker focused on cleaning the metallic surface of the turbine. The power plant's interior is visible, featuring high ceilings, large machinery, and industrial pipes, all bathed in artificial lighting. The worker's attire, which includes a hard hat and protective gloves, emphasizes safety protocols in the industrial setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm deforms during the wiping process, and the hand becomes deformed."
}
] |
seed46_2082
|
videos/HRA_part2/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1896
|
videos/HRA_part0/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Normal. The cat's limbs are poorly generated, the tail is too long, and the facial features have not been generated. The astronaut's body has also not been generated."
}
] |
seed44_1948
|
videos/HRA_part1/1948.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, clad in a gray shirt and khaki pants, interacts with a sleek black jaguar at the edge of a tranquil pool. The engineer, displaying remarkable courage, gently touches the big cat's nose. Moments later, the jaguar, showcasing its powerful physique, leaps into the water, its muscles rippling beneath its glossy coat. The engineer watches with awe as the jaguar swims effortlessly, its fluid movements captivating against the serene aquatic backdrop. Throughout, the engineer remains composed, observing the majestic animal from a safe distance by the poolside.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the engineer touching the jaguar's nose, or the jaguar leaping into the water to swim."
}
] |
seed46_1174
|
videos/HRA_part2/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1729
|
videos/HRA_part1/1729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 adorable otter, with a round face and curious eyes, walks on its hind legs across a wooden boardwalk, holding a small fish in its front paws. It wears a tiny red scarf around its neck, adding a touch of whimsy to the scene. The otter's brown fur contrasts against the light wooden planks, while the lush greenery and calm water of a pond can be seen in the background, creating a serene and picturesque environment. The otter's confident stride and the fish it carries suggest it has just enjoyed a meal, making the scene both charming and heartwarming.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2106
|
videos/HRA_part0/2106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a black vest, button-down shirt, and striped tie, meticulously mops the floor of an empty restaurant with white walls and ceiling, wooden tables and chairs, and large windows. The room is illuminated by soft artificial lighting, casting a warm glow on the clean, wet floor. The waiter's movements are deliberate and focused, his mop leaving a trail of cleanliness across the tile surface. In the background, a fully set table with a white cloth, silverware, and glasses awaits the next guests, while a row of wine bottles sits on a shelf above. The scene conveys a sense of preparation and attention to detail, as the waiter ensures the dining area is spotless for the upcoming service.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2822
|
videos/HRA_part1/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's fingers are deformed, the face is blurry, and the camera is deformed."
}
] |
seed44_1891
|
videos/HRA_part1/1891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 airport terminal, a large, lifelike panda costume lays on its side, partially inflated, as a person inside attempts to crawl into it. The individual struggles comically within the confines of the costume, drawing curious glances from nearby travelers. Once fully inside, the person begins to crawl across the airport floor, the oversized panda head bouncing with each movement, creating a surreal and amusing scene amidst the typical airport chaos. Passengers of all ages watch in amusement, some capturing the unusual sight on their phones, as the person in the panda suit continues to crawl, adding a touch of whimsy to the otherwise ordinary airport environment.]"
},
{
"from": "gpt",
"value": "Bad. The panda's head, arms, and legs are distorted, as well as the bodies and faces of the surrounding crowd."
}
] |
seed46_2039
|
videos/HRA_part2/2039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cosmic setting, a majestic cheetah, adorned with a golden collar and walking on zero-gravity platforms, traverses through an infinite space library. Surrounded by floating bookshelves filled with ancient tomes, the cheetah moves gracefully, its gaze focused on a distant celestial body. The library, illuminated by ethereal starlight, showcases an array of knowledge from across the universe, with the cheetah embodying wisdom and power as it explores this otherworldly domain.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's movements in the video are uncoordinated."
}
] |
seed42_3178
|
videos/HRA_part0/3178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a red beret and carrying a large canvas, walks purposefully down a bustling city street lined with vintage cinemas. Each theater features marquee signs advertising classic films from the golden age of cinema. The artist's attire includes a striped shirt, dark trousers, and a pair of worn-out sneakers, giving a sense of his creative and casual lifestyle. As he strides, passersby glance curiously at his oversized artwork, which is draped in a protective cloth, hinting at the mystery and anticipation of his latest creation. The vibrant atmosphere of the old movie houses and the artist's journey through the urban landscape evoke a sense of nostalgia and artistic inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1523
|
videos/HRA_part1/1523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2478
|
videos/HRA_part1/2478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, wearing a black t-shirt, showcases a ferret jumping from his right shoulder onto his left arm. Set against a dark grey background, the scene highlights the ferret's agility and the actor's engagement with the small animal. The actor's facial expression conveys amusement and surprise, emphasizing the playful interaction between man and pet. Throughout the sequence, the ferret performs several jumps, each time landing gracefully on different parts of the actor's body, while he remains fully engaged and attentive, his black t-shirt providing a stark contrast against the neutral backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's movement from the actor's right shoulder to the left arm in the video is not continuous and smooth, showing some coordination issues."
}
] |
seed42_1055
|
videos/HRA_part0/1055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative musician, adorned in a casual outfit featuring a gray turtleneck sweater and dark pants, sits on a wooden chair in a cozy, dimly lit room. Surrounded by musical instruments, the artist focuses intently on knitting a vibrant red scarf, demonstrating a surprising talent beyond music. The scene captures the individual's dual passions, highlighting their artistic versatility as they skillfully knit while sitting amongst guitars and sheet music, basking in the warm glow of a single lamp.]"
},
{
"from": "gpt",
"value": "Normal. The finger generation of the character in the video is problematic."
}
] |
seed42_1484
|
videos/HRA_part0/1484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious, softly lit room with a neutral color palette, two children, a boy and a girl, both wearing pajamas, are seen playing together. The boy, wearing blue pajamas, crawls across the floor, while the girl, dressed in pink pajamas, manipulates a gravity control device, causing everyday objects to float around them. The floating items include a teddy bear, a toy car, and a book, creating a whimsical atmosphere. The children laugh and play among the floating objects, the girl adjusting the gravity device to move the items closer or further away, all within the cozy, safe environment of their playroom.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2160
|
videos/HRA_part1/2160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling park setting, two children engage in playful pushing, wearing vibrant, colorful clothing typical of a sunny day. One child, dressed in a yellow shirt and blue shorts, playfully pushes another child, who is wearing a red shirt and green shorts, against the backdrop of lush green grass and clear blue skies. The interaction is filled with laughter and joy, capturing the essence of innocent childhood fun. The children's faces are beaming with delight, their eyes sparkling with excitement, as they enjoy each other's company in the heart of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the two children playing and shoving each other in the video are discontinuous, with abrupt changes."
}
] |
seed44_3192
|
videos/HRA_part1/3192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed sports arena, a young female cashier, wearing a white apron over her outfit, diligently wipes down the countertop with a cloth. The background is vibrant, featuring neon lights and digital screens displaying scores from ongoing cosmic games. The cashier's actions are methodical, her focus intense, as she ensures the counter is spotless for the next customer in this bustling, intergalactic sports hub. Behind her, patrons in diverse alien attire wait patiently, adding to the dynamic atmosphere of this extraterrestrial venue.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2822
|
videos/HRA_part1/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Good. The cleaner's movements in the video are basically normal."
}
] |
seed44_1044
|
videos/HRA_part1/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1456
|
videos/HRA_part0/1456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video turns and walks unsmoothly, with uncoordinated movements."
}
] |
seed46_1646
|
videos/HRA_part2/1646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a brown jacket over a green shirt, leans over the railing of a pier to fish, with a small fishing rod in hand and a yellow bucket by his side. He is seen from behind, gazing intently into the water, the sun reflecting off his balding head and casting a warm glow on his upturned face. The pier is old and weathered, with faded paint and worn wooden planks, and the water below is calm and clear, dotted with the occasional ripple from a fish. In the distance, a city skyline can be seen, its tall buildings silhouetted against the bright blue sky, providing a stark contrast to the peaceful scene unfolding on the pier.]"
},
{
"from": "gpt",
"value": "Normal. The character's head and hands are distorted in the video."
}
] |
seed42_1790
|
videos/HRA_part0/1790.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 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 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": "Bad. The osprey's wings in the video have issues, the face is generated blurry, the claws are not generated, and the body is deformed."
}
] |
seed46_3211
|
videos/HRA_part2/3211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]"
},
{
"from": "gpt",
"value": "Bad. The artist's running motion in the video is not smooth."
}
] |
seed46_2484
|
videos/HRA_part2/2484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic albatross soars through a dramatic sky filled with billowing clouds, its expansive wingspan casting a shadow on the turbulent sea far below. The bird's plumage is a stunning contrast of pure white underparts and sleek, dark upperwings, accentuated by the golden hue of the setting sun. Its sharp, hooked bill and piercing eyes are focused ahead, embodying the spirit of freedom and grace as it navigates the vast, open ocean with effortless elegance. The scene is framed by the rugged coastline in the distance, highlighting the albatross's natural habitat and its role as a symbol of resilience and adaptability in the face of nature's challenges.]"
},
{
"from": "gpt",
"value": "Bad. The albatross's claws are twisted, wings are twisted, and head is twisted."
}
] |
seed42_1879
|
videos/HRA_part0/1879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged, balding teacher sits slumped at a large wooden desk, surrounded by stacks of books and papers, in a dimly lit room. His glasses have slipped down his nose, and his head rests on a pile of graded exams, indicating exhaustion from late-night grading. The cluttered desk, filled with educational materials, suggests a dedicated educator overwhelmed by his workload. Behind him, a window reveals the glow of streetlights outside, hinting at the late hour. The teacher's weary posture and closed eyes depict a moment of much-needed rest amidst the demands of his profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1157
|
videos/HRA_part1/1157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 station pool, a courageous nurse, wearing a protective spacesuit with a clear helmet, fearlessly swims alongside a non-venomous cobra, which has been specially adapted for space travel. The nurse's spacesuit is adorned with patches representing various medical organizations, highlighting her dedication to healthcare even in the cosmos. The cobra, now a docile companion, glides effortlessly through the water, its scales reflecting the artificial lighting of the space station. This extraordinary scene showcases the integration of healthcare, exotic animals, and space tourism in a serene aquatic environment, encapsulating the essence of adventure and innovation in the final frontier.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's movements in the video are not smooth."
}
] |
seed46_1910
|
videos/HRA_part2/1910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow safety vest, orange hard hat, and blue jeans, sits on a wooden beam, holding a hammer in his right hand and resting his left elbow on his knee, against a backdrop of a partially built structure with blue skies visible through the gaps. Moments later, he takes a break, sitting on the same beam with his legs crossed, now holding a water bottle and looking directly at the camera. Then, he is shown sitting with his legs dangling, his right arm resting on a higher beam, and his left hand holding the hammer, with the half-constructed building and clear blue sky in the background. Lastly, he sits with his back straight, both hands on his knees, and a focused expression, still clad in his yellow vest, orange helmet, and denim pants, the unfinished building and open sky framing him.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, and twisted legs."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.