id
stringlengths 2
214
| conversations
listlengths 2
42
| data_source
stringclasses 54
values |
|---|---|---|
vision-flan_places365+Image_Classification+attic_00002094.jpg
|
[
{
"from": "human",
"value": "Your task involves analyzing an image of a scene and identifying the appropriate name for that particular scene. Examples of scene names could include airfield, airplane cabin, airport terminal, alcove, alley, amphitheater, amusement arcade, etc. "
},
{
"from": "gpt",
"value": "attic"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+house_image_category_classification+pic_216.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a house. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Cartoon (b) Art painting (c) Sketch (d) Photograph"
},
{
"from": "gpt",
"value": "(a) Cartoon"
}
] |
vision_flan(filtered)
|
vision-flan_MEMOTION+sentiment_detection+image_2664.jpg
|
[
{
"from": "human",
"value": "Can you please read the image and extract all the text from it?"
},
{
"from": "gpt",
"value": "YOU CLAIM TO WANT TO MAKE AMERICA GREAT BUT YOUR RACISM MISOGYNY AND INABILITY TO SEE ANYONE ELSE'S POINT OF VIEW WOULD DETERMINE THAT TO BE A LIE imgflip.com"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+horse_image_category_classification+n02374451_468-10.png
|
[
{
"from": "human",
"value": "You will be given an image of a horse. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Photograph (b) Cartoon (c) Art painting (d) Sketch"
},
{
"from": "gpt",
"value": "(d) Sketch"
}
] |
vision_flan(filtered)
|
vision-flan_LSUN+Image_Classification+living_room_113.png
|
[
{
"from": "human",
"value": "In this task you will be provided with a picture of a scene(dining room, bedroom, kitchen, outdoor church, and so on) and you have to classify images into their corresponding scene categories. Your answer should be the name of the place.\nOptions: (a) classroom (b) tower (c) kitchen (d) church outside (e) restaurant (f) bedroom (g) dining room (h) living room (i) conference room"
},
{
"from": "gpt",
"value": "(h) living room"
}
] |
vision_flan(filtered)
|
vision-flan_DTD+all_texture_detection++pleated/pleated_0058.jpg
|
[
{
"from": "human",
"value": "Texture is defined as the feel, appearance or consistency of a surface or substance from a human's perspective. Detect all the textures in the image. Present it as a comma separated list"
},
{
"from": "gpt",
"value": "pleated"
}
] |
vision_flan(filtered)
|
vision-flan_coco+image_classification_kitchen+19853
|
[
{
"from": "human",
"value": "Given an image of something from the kitchen, identify what it could be. The image could be of cooking tools or items that are used for eating. It could also be used for serving food or storing it.\nOptions: (a) This image contains a fork (b) This image contains a bottle (c) This image contains a wine glass (d) This image contains a cup (e) This image contains a bowl (f) This image contains a spoon (g) This image contains a knife"
},
{
"from": "gpt",
"value": "(d) This image contains a cup"
}
] |
vision_flan(filtered)
|
vision-flan_coco+image_classification_kitchen+1092
|
[
{
"from": "human",
"value": "Given an image of something from the kitchen, identify what it could be. The image could be of cooking tools or items that are used for eating. It could also be used for serving food or storing it.\nOptions: (a) This image contains a knife (b) This image contains a bowl (c) This image contains a wine glass (d) This image contains a fork (e) This image contains a bottle (f) This image contains a spoon (g) This image contains a cup"
},
{
"from": "gpt",
"value": "(e) This image contains a bottle"
}
] |
vision_flan(filtered)
|
vision-flan_DeepFashion_highres_Attribute_and_Category+Cloth_Classification+img_highres_subset_Striped_Print_Maxi_Dress-img_00000015.jpg
|
[
{
"from": "human",
"value": "Can you write a very short description of the cloth?"
},
{
"from": "gpt",
"value": "The cloth is a Striped Print Maxi Dress."
}
] |
vision_flan(filtered)
|
vision-flan_trainSet+image_classification+073
|
[
{
"from": "human",
"value": "Using one word, classify the type of distortion / style is applied to the image or what type of setting is represented in the image."
},
{
"from": "gpt",
"value": "Action"
}
] |
vision_flan(filtered)
|
vision-flan_semart+image_school+14080
|
[
{
"from": "human",
"value": "I would like to know what school of art this painting could be from. Some possible schools of art are Italian, German, or Spanish among others"
},
{
"from": "gpt",
"value": "This painting comes from the school of Italian art "
}
] |
vision_flan(filtered)
|
vision-flan_VisDA-2017+image_classification+src_5_1-1-1__146_349_150
|
[
{
"from": "human",
"value": "Your task is to classify an image based on its corresponding object category. The image contains a variety of objects distributed among 12 categories, including aeroplane, horse, knife, person, plant, and others. To accurately classify the image, carefully analyze its visual characteristics, such as shape, color, texture, and spatial context relations, as these attributes can vary significantly across different domains. Once you have identified the object category of the image, output the appropriate label for your classification."
},
{
"from": "gpt",
"value": "plant"
}
] |
vision_flan(filtered)
|
vision-flan_Places205+Image_env_classification+gsun_188dfac87273e6d58716319c552b256b
|
[
{
"from": "human",
"value": "In this task, you have to identify if the place or scene pictured is indoor or outdoor. In the image is among a total of 205 classes such as Hospital, Bridge, Courtyard, Motel,.... The classes of the images are a diverse set of places or scenes. Pay attention to the details as some of the images may contain an object that relates to a specific place while some images may directly show the place or scenary. So, your answer should be the place or scene shown in the image\nOptions: (a) Outdoor (b) Indoor"
},
{
"from": "gpt",
"value": "(a) Outdoor"
}
] |
vision_flan(filtered)
|
multiinstruct_2408742_186455
|
[
{
"from": "human",
"value": "How many phones are there?\n\nOptions: (a) 15. (b) 14 phones. (c) 6. (d) 8."
},
{
"from": "gpt",
"value": "(b) 14 phones."
}
] |
vision_flan(filtered)
|
vision-flan_coco+image_classification_animal+23883
|
[
{
"from": "human",
"value": "Given an image of an animal, identify the kind of animal in the image. The picture could be of more popular animals that are visible around zoos or are sometimes domesticated at home. They could also sometimes be found in the wild.\nOptions: (a) This image contains a horse (b) This image contains a sheep (c) This image contains a dog (d) This image contains a bird (e) This image contains a bear (f) This image contains a cow (g) This image contains a zebra (h) This image contains a giraffe (i) This image contains a cat (j) This image contains an elephant"
},
{
"from": "gpt",
"value": "(d) This image contains a bird"
}
] |
vision_flan(filtered)
|
multiinstruct_2341287_778390
|
[
{
"from": "human",
"value": "Who is wearing a shirt?\n\nOptions: (a) The boy. (b) The woman. (c) The teacher. (d) A man."
},
{
"from": "gpt",
"value": "(d) A man."
}
] |
vision_flan(filtered)
|
vision-flan_PACS+house_image_category_classification+pic_113.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a house. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Cartoon (b) Photograph (c) Art painting (d) Sketch"
},
{
"from": "gpt",
"value": "(b) Photograph"
}
] |
vision_flan(filtered)
|
vision-flan_ImageNet-R+image_domain_classification+videogame_17
|
[
{
"from": "human",
"value": "Your goal is to classify the image based on its domain, which can be 'videogame', 'painting', 'sketch', 'cartoon', 'art', 'toy', 'deviantart', 'graphic', 'sculpture', 'misc', 'embroidery', 'sticker', 'graffiti', 'origami', or 'tattoo'. Your final output should specify the identified domain of the image."
},
{
"from": "gpt",
"value": "videogame"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+house_image_category_classification+pic_264.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a house. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Art painting (b) Photograph (c) Sketch (d) Cartoon"
},
{
"from": "gpt",
"value": "(b) Photograph"
}
] |
vision_flan(filtered)
|
vision-flan_MEMOTION+sentiment_detection+image_1716.jpg
|
[
{
"from": "human",
"value": "Can you please read the image and extract all the text from it?"
},
{
"from": "gpt",
"value": "ThronesMemes OMG HE'S AMAZING WITH KIDS TOO"
}
] |
vision_flan(filtered)
|
vision-flan_spot-the-diff+image_diff_identification+13313
|
[
{
"from": "human",
"value": "You are provided with an image which contains two pictures side by side. Your task is to identify the differences between the two pictures. Separate the differences with a comma."
},
{
"from": "gpt",
"value": "there is no bus in this picture, there is no black car behind the bus, the man is on the left side of the sign not in front of it"
}
] |
vision_flan(filtered)
|
vision-flan_coco+image_classification_kitchen+8786
|
[
{
"from": "human",
"value": "Given an image of something from the kitchen, identify what it could be. The image could be of cooking tools or items that are used for eating. It could also be used for serving food or storing it.\nOptions: (a) This image contains a fork (b) This image contains a cup (c) This image contains a bowl (d) This image contains a wine glass (e) This image contains a bottle (f) This image contains a spoon (g) This image contains a knife"
},
{
"from": "gpt",
"value": "(e) This image contains a bottle"
}
] |
vision_flan(filtered)
|
vision-flan_VQG+question_generation+ab99da85-91d6-49df-a317-197156ffeada_2
|
[
{
"from": "human",
"value": "Given an image, generate a relevant question about the content of the image."
},
{
"from": "gpt",
"value": "Where did you find a pitcher in that color?"
}
] |
vision_flan(filtered)
|
vision-flan_Office_31+Image_Classification_ObjectAndCategory_amazon_ruler_frame_0073.jpg
|
[
{
"from": "human",
"value": "The input for this task is an image of the commonly encountered office objects such as keyboards, file cabinets, and laptops from three different categories(AMAZON, DSLR, WEBCAM). The output of this task is to name the domain of image(AMAZON, DSLR, or WEBCAM) as well as the object in the image in the following format: 'Category ObjectName' (exp. amazon mug) AMAZON: these images were captured from a website of online merchants, they are captured against clean background. DSLR cameras offer improved image quality when compared to standard webcams."
},
{
"from": "gpt",
"value": "amazon ruler"
}
] |
vision_flan(filtered)
|
vision-flan_MVTecAD+image_classification+334
|
[
{
"from": "human",
"value": "Your objective is to classify an image based on its corresponding object category. The image provided encompasses a diverse range of industrial items, including a bottle, cable, carpet, and more. Focus on the overall visual appearance of the image, paying attention to details such as lines, shading, color scheme, and level of detail. It is crucial to analyze the distinctive characteristics of the object, such as its shape, color, and texture, as these features may vary significantly between different object categories. Once you have completed the classification process, output the appropriate object name based on your analysis."
},
{
"from": "gpt",
"value": "The object is a hazelnut."
}
] |
vision_flan(filtered)
|
vision-flan_coco+image_classification_kitchen+41525
|
[
{
"from": "human",
"value": "Given an image of something from the kitchen, identify what it could be. The image could be of cooking tools or items that are used for eating. It could also be used for serving food or storing it.\nOptions: (a) This image contains a bowl (b) This image contains a knife (c) This image contains a fork (d) This image contains a cup (e) This image contains a bottle (f) This image contains a spoon (g) This image contains a wine glass"
},
{
"from": "gpt",
"value": "(c) This image contains a fork"
}
] |
vision_flan(filtered)
|
vision-flan_LAD+object_detection_details+ab1b4361f9690c519705cf24e7b4af54.jpg
|
[
{
"from": "human",
"value": "I'll give you an image. What is the main object in it? Please give additional details."
},
{
"from": "gpt",
"value": "The object in the image is dreadlocks. It is brown, fits people with small eyes, fits fair-skinned people, fits people with a pointed nose, fits people with ear rings, fits people with heavy make-up, is easy to be messy, is gorgeous, is cute, is cool, is lively"
}
] |
vision_flan(filtered)
|
vision-flan_MemeCap+image_captioning+yt2eog_1
|
[
{
"from": "human",
"value": "You are given a meme and your goal is to generate a caption that describes the image. Ignore the text in the meme.\n\nTitle: Yes. I'm guilty too."
},
{
"from": "gpt",
"value": "A man in a yellow suit peeks out from behind a tree while rubbing his hands together and licking his lips."
}
] |
vision_flan(filtered)
|
vision-flan_VQG+question_generation+36ced183-d916-4221-99d9-55de3001c332_1
|
[
{
"from": "human",
"value": "Given an image, generate a relevant question about the content of the image."
},
{
"from": "gpt",
"value": "Whose farm is this?"
}
] |
vision_flan(filtered)
|
vision-flan_cinic-10+image_classification_animal+92274
|
[
{
"from": "human",
"value": "The given image can contain various types of animals. Some of these animals are found in forests, drylands, or other natural areas. Some of them could also be domesticated pets. Please identify the animal in the picture."
},
{
"from": "gpt",
"value": "The image contains a frog"
}
] |
vision_flan(filtered)
|
vision-flan_VQG+question_generation+3337214__93282_3
|
[
{
"from": "human",
"value": "Given an image, generate a relevant question about the content of the image."
},
{
"from": "gpt",
"value": "What is the girl's name?"
}
] |
vision_flan(filtered)
|
vision-flan_Winoground+image_captioning+95+image_1
|
[
{
"from": "human",
"value": "In this task, you will be provided with an image and two captions. Your task is to identify which of the two captions correctly describes the image.\nOptions: (a) hammering a hand (b) handing a hammer"
},
{
"from": "gpt",
"value": "(a) hammering a hand"
}
] |
vision_flan(filtered)
|
vision-flan_MEMOTION+sentiment_detection+image_4716.png
|
[
{
"from": "human",
"value": "Can you please read the image and extract all the text from it?"
},
{
"from": "gpt",
"value": "IF A TREE FALLS IN WASHINGTON INSTALARE DOES ANYBODY HEAR IT OR IS IT OBAMA'S FAULT? More funny Obama memes: http://bit.ly/agBCjz"
}
] |
vision_flan(filtered)
|
vision-flan_FoodLogoDet-1500+food_logo_recognition+015198
|
[
{
"from": "human",
"value": "What is the logo in the image?"
},
{
"from": "gpt",
"value": "The logo in the image is ching's secret."
}
] |
vision_flan(filtered)
|
vision-flan_PACS+horse_image_category_classification+n02374451_14846-3.png
|
[
{
"from": "human",
"value": "You will be given an image of a horse. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Art painting (b) Sketch (c) Cartoon (d) Photograph"
},
{
"from": "gpt",
"value": "(b) Sketch"
}
] |
vision_flan(filtered)
|
vision-flan_Office_31+Image_Classification_Category_amazon_speaker_frame_0041.jpg
|
[
{
"from": "human",
"value": "The input for this task is an image of commonly encountered office objects such as keyboards, file cabinets, and laptops from three different categories(AMAZON, DSLR, WEBCAM). The output of this task is to name the domains of the image(AMAZON, DSLR, or WEBCAM). AMAZON: These images were captured from a website of online merchants, they are captured against a clean background. DSLR cameras offer improved image quality when compared to standard webcams.\nOptions: (a) webcam (b) amazon (c) dslr"
},
{
"from": "gpt",
"value": "(b) amazon"
}
] |
vision_flan(filtered)
|
vision-flan_recipe-qa+visual_coherence+6357
|
[
{
"from": "human",
"value": "The given image contains 4 image choices numbered A through D. Select the least similar image among the gorup"
},
{
"from": "gpt",
"value": "The least similar image is A"
}
] |
vision_flan(filtered)
|
vision-flan_CoVA+webpage_recognition+13333
|
[
{
"from": "human",
"value": "What is the name of the website based on the given image?"
},
{
"from": "gpt",
"value": "The name of the website is www.walmart.com."
}
] |
vision_flan(filtered)
|
vision-flan_recipe-qa+visual_coherence+3031
|
[
{
"from": "human",
"value": "The given image contains 4 image choices numbered A through D. Select the least similar image among the gorup"
},
{
"from": "gpt",
"value": "The least similar image is B"
}
] |
vision_flan(filtered)
|
vision-flan_MEMOTION+sentiment_detection+image_5111.jpg
|
[
{
"from": "human",
"value": "Can you please read the image and extract all the text from it?"
},
{
"from": "gpt",
"value": "Russo Brothers say the Avengers 4 Title was said in a previous Marvel Movie That up there that's the endgame. How were you guys planning on beating that?"
}
] |
vision_flan(filtered)
|
vision-flan_VisDA-2017+image_classification+src_2_02924116_57e1aa38fcc42438d3a958737449e7cb__231_10_165
|
[
{
"from": "human",
"value": "Your task is to classify an image based on its corresponding object category. The image contains a variety of objects distributed among 12 categories, including aeroplane, horse, knife, person, plant, and others. To accurately classify the image, carefully analyze its visual characteristics, such as shape, color, texture, and spatial context relations, as these attributes can vary significantly across different domains. Once you have identified the object category of the image, output the appropriate label for your classification."
},
{
"from": "gpt",
"value": "bus"
}
] |
vision_flan(filtered)
|
vision-flan_Office_31+Image_Classification_Category_amazon_paper_notebook_frame_0071.jpg
|
[
{
"from": "human",
"value": "The input for this task is an image of commonly encountered office objects such as keyboards, file cabinets, and laptops from three different categories(AMAZON, DSLR, WEBCAM). The output of this task is to name the domains of the image(AMAZON, DSLR, or WEBCAM). AMAZON: These images were captured from a website of online merchants, they are captured against a clean background. DSLR cameras offer improved image quality when compared to standard webcams.\nOptions: (a) dslr (b) webcam (c) amazon"
},
{
"from": "gpt",
"value": "(c) amazon"
}
] |
vision_flan(filtered)
|
vision-flan_Places205+Image_env_classification+gsun_69ac0cb5e8e3f275ff23f172c65a643f
|
[
{
"from": "human",
"value": "In this task, you have to identify if the place or scene pictured is indoor or outdoor. In the image is among a total of 205 classes such as Hospital, Bridge, Courtyard, Motel,.... The classes of the images are a diverse set of places or scenes. Pay attention to the details as some of the images may contain an object that relates to a specific place while some images may directly show the place or scenary. So, your answer should be the place or scene shown in the image\nOptions: (a) Outdoor (b) Indoor"
},
{
"from": "gpt",
"value": "(b) Indoor"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+house_image_category_classification+pic_203.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a house. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Cartoon (b) Art painting (c) Photograph (d) Sketch"
},
{
"from": "gpt",
"value": "(c) Photograph"
}
] |
vision_flan(filtered)
|
vision-flan_cinic-10+image_classification_animal+96314
|
[
{
"from": "human",
"value": "The given image can contain various types of animals. Some of these animals are found in forests, drylands, or other natural areas. Some of them could also be domesticated pets. Please identify the animal in the picture."
},
{
"from": "gpt",
"value": "The image contains a frog"
}
] |
vision_flan(filtered)
|
vision-flan_VisDA-2017+object_classification_train_motorcycle_672
|
[
{
"from": "human",
"value": "You are given an image which contains a 3D rendered object. Your goal is to identify the category of the object present in the image from the given options.\nOptions: (a) train (b) plant (c) bus (d) motorcycle (e) car (f) knife (g) skateboard (h) aeroplane (i) horse (j) truck"
},
{
"from": "gpt",
"value": "(d) motorcycle"
}
] |
vision_flan(filtered)
|
multiinstruct_2341528_650241
|
[
{
"from": "human",
"value": "What color is the nearest woman's t-shirt?\n\nOptions: (a) Gray. (b) White. (c) Red. (d) Green."
},
{
"from": "gpt",
"value": "(a) Gray."
}
] |
vision_flan(filtered)
|
vision-flan_DeepFashion_highres_Attribute_and_Category+Cloth_Classification+img_highres_subset_Camo_Print_Shorts-img_00000084.jpg
|
[
{
"from": "human",
"value": "Can you write a very short description of the cloth?"
},
{
"from": "gpt",
"value": "The cloth is a Camo Print Shorts."
}
] |
vision_flan(filtered)
|
vision-flan_VQG+caption_generation+af9c9fc5-19bb-4dbe-8045-3e4f903994be_1
|
[
{
"from": "human",
"value": "Given an image, you will generate a caption for the image."
},
{
"from": "gpt",
"value": "A blue water pump"
}
] |
vision_flan(filtered)
|
vision-flan_WIT+detailed_description+Deux-Acren_%28Lessines%29_-_Grand_Prix_Criquielion%2C_17_mai_2014%2C_arriv%C3%A9e_%28B23%29.JPG
|
[
{
"from": "human",
"value": "Give me some background knowledge about this image."
},
{
"from": "gpt",
"value": "Kevin Deltombe is a Belgian cyclist, who currently rides for UCI ProTeam Sport Vlaanderen–Baloise."
}
] |
vision_flan(filtered)
|
vision-flan_VOC2007+object_detection+002250.jpg
|
[
{
"from": "human",
"value": "Identify some objects that are present in the image. Give a comma separated list as the output."
},
{
"from": "gpt",
"value": "person"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+horse_image_category_classification+n02374451_13132-4.png
|
[
{
"from": "human",
"value": "You will be given an image of a horse. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Photograph (b) Cartoon (c) Sketch (d) Art painting"
},
{
"from": "gpt",
"value": "(c) Sketch"
}
] |
vision_flan(filtered)
|
vision-flan_MVTecAD+image_classification+073
|
[
{
"from": "human",
"value": "Your objective is to classify an image based on its corresponding object category. The image provided encompasses a diverse range of industrial items, including a bottle, cable, carpet, and more. Focus on the overall visual appearance of the image, paying attention to details such as lines, shading, color scheme, and level of detail. It is crucial to analyze the distinctive characteristics of the object, such as its shape, color, and texture, as these features may vary significantly between different object categories. Once you have completed the classification process, output the appropriate object name based on your analysis."
},
{
"from": "gpt",
"value": "The object is a screw."
}
] |
vision_flan(filtered)
|
vision-flan_MemeCap+meme_captioning+z6cio5_1
|
[
{
"from": "human",
"value": "Generate a caption for the given meme.\n\nTitle: Canada works so hard, theyve earned the right to brag"
},
{
"from": "gpt",
"value": "Meme poster is trying to convey that though Croatia defeats the meme poster by a huge margin, the meme poster is celebrating its first medal."
}
] |
vision_flan(filtered)
|
vision-flan_ImageNet-C+image_classification_weather+546339
|
[
{
"from": "human",
"value": "Given an image, identify what kind of weather conditions might have corrupted the image. It can be different types of bad weather or outdoor conditions\nOptions: (a) The corruption type is brightness (b) The corruption type is fog (c) The corruption type is frost (d) The corruption type is snow"
},
{
"from": "gpt",
"value": "(b) The corruption type is fog"
}
] |
vision_flan(filtered)
|
vision-flan_STVQA+image_question_answer+n03393912_7802.JPEG
|
[
{
"from": "human",
"value": "The input text contains a question about the image. Please answer the question.\n\nWhat is the number code written on the train?"
},
{
"from": "gpt",
"value": "528818"
}
] |
vision_flan(filtered)
|
vision-flan_recipe-qa+visual_coherence+5746
|
[
{
"from": "human",
"value": "The given image contains 4 image choices numbered A through D. Select the least similar image among the gorup"
},
{
"from": "gpt",
"value": "The least similar image is B"
}
] |
vision_flan(filtered)
|
vision-flan_ImageNet-A+image_classification+5361
|
[
{
"from": "human",
"value": "In this task, given an image, please identify what the image contains a. The image could contain, among other things, animals, birds, daily objects, insects\nOptions: (a) The provided image contains a quill (b) The provided image contains a porcupine (c) The provided image contains a bow (d) The provided image contains a syringe (e) The provided image contains a pomegranate (f) The provided image contains a harvestman (g) The provided image contains a German Shepherd Dog (h) The provided image contains a go-kart"
},
{
"from": "gpt",
"value": "(b) The provided image contains a porcupine"
}
] |
vision_flan(filtered)
|
vision-flan_Office_31+Image_Classification_Category_amazon_laptop_computer_frame_0019.jpg
|
[
{
"from": "human",
"value": "The input for this task is an image of commonly encountered office objects such as keyboards, file cabinets, and laptops from three different categories(AMAZON, DSLR, WEBCAM). The output of this task is to name the domains of the image(AMAZON, DSLR, or WEBCAM). AMAZON: These images were captured from a website of online merchants, they are captured against a clean background. DSLR cameras offer improved image quality when compared to standard webcams.\nOptions: (a) dslr (b) amazon (c) webcam"
},
{
"from": "gpt",
"value": "(b) amazon"
}
] |
vision_flan(filtered)
|
vision-flan_VQG+caption_generation+aef727e5-da16-44c4-9af3-d9ff25ea3a9d_4
|
[
{
"from": "human",
"value": "Given an image, you will generate a caption for the image."
},
{
"from": "gpt",
"value": "A little girl sets up felt squares on a table"
}
] |
vision_flan(filtered)
|
vision-flan_HICO+human_activity_detection+HICO_test2015_00009111.jpg
|
[
{
"from": "human",
"value": "Answer a simple question. What is the person in the image doing? If there is no action being performed, describe the main object in the image."
},
{
"from": "gpt",
"value": "A person is driving the boat."
}
] |
vision_flan(filtered)
|
vision-flan_coco+image_classification_kitchen+36620
|
[
{
"from": "human",
"value": "Given an image of something from the kitchen, identify what it could be. The image could be of cooking tools or items that are used for eating. It could also be used for serving food or storing it.\nOptions: (a) This image contains a spoon (b) This image contains a bowl (c) This image contains a cup (d) This image contains a bottle (e) This image contains a wine glass (f) This image contains a fork (g) This image contains a knife"
},
{
"from": "gpt",
"value": "(c) This image contains a cup"
}
] |
vision_flan(filtered)
|
vision-flan_recipe-qa+visual_coherence+5717
|
[
{
"from": "human",
"value": "The given image contains 4 image choices numbered A through D. Select the least similar image among the gorup"
},
{
"from": "gpt",
"value": "The least similar image is D"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+horse_image_category_classification+pic_049.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a horse. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Sketch (b) Art painting (c) Cartoon (d) Photograph"
},
{
"from": "gpt",
"value": "(c) Cartoon"
}
] |
vision_flan(filtered)
|
vision-flan_ayahoo_test_images+animal_object_vehicle_image_classification+donkey_100
|
[
{
"from": "human",
"value": "In this task, you are given an image from a dataset, which contains images from different categories of animals, objects, and vehicles. These categories further divide into subcategories. Your job is to classify the given image into one of these subcategories, which could be anything from an aeroplane to a zebra. Your classification should be based on key identifiers like size, shape, color, distinctive features, and the context or environment depicted in the image. For example, if you're given an image of a zebra, your answer would simply be zebra. Remember that images could be of objects or vehicles as well. Your answer should be a single word representing the appropriate subcategory for the image, emphasizing specificity beyond the broad categories."
},
{
"from": "gpt",
"value": "donkey"
}
] |
vision_flan(filtered)
|
vision-flan_visdial+answer_question_4+116871
|
[
{
"from": "human",
"value": "This is a short conversation between two people, represented as A and B. They are talking about the given picture and are discussing some questions about it. Pay attention to the conversation and answer the question.\n\nA: is the photo in color?\nB: yes\nA: what color are the peppers?\nB: yes, there is peppers in a bowl\nA: what color are they?\nB: green and red\nA: is the bowl on a table?\nB: yes\nQuestion: is there anything else on the table?"
},
{
"from": "gpt",
"value": "yes, there is a cup and a lid"
}
] |
vision_flan(filtered)
|
vision-flan_semart+image_school+6200
|
[
{
"from": "human",
"value": "I would like to know what school of art this painting could be from. Some possible schools of art are Italian, German, or Spanish among others"
},
{
"from": "gpt",
"value": "This painting comes from the school of Dutch art "
}
] |
vision_flan(filtered)
|
vision-flan_PACS+house_image_category_classification+pic_208.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a house. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Sketch (b) Photograph (c) Art painting (d) Cartoon"
},
{
"from": "gpt",
"value": "(b) Photograph"
}
] |
vision_flan(filtered)
|
vision-flan_vizwiz+question_answer+13948
|
[
{
"from": "human",
"value": "A blind person asks you a question about this image, answer the question in the best way possible.\n\nWhat kind of shampoo is this?\nOptions: (a) bed head (b) bedhead control freak (c) bed head control freak (d) bead head"
},
{
"from": "gpt",
"value": "(c) bed head control freak"
}
] |
vision_flan(filtered)
|
vision-flan_KVQA+image_question_answer+46697.JPG+15
|
[
{
"from": "human",
"value": "You are provided with a picture and a question related to the picture. Your job is to correctly answer the question. Note that any references to directions (left, right, center, etc.) in the questions are from the perspective of the person depicted in the image.\n\nDo people in the image belong to the same political party?"
},
{
"from": "gpt",
"value": "Yes"
}
] |
vision_flan(filtered)
|
vision-flan_STL-10+Image_Classification+truck_4301.png
|
[
{
"from": "human",
"value": "You will be presented with an image and your objective is to identify and name the object depicted in the image.\nOptions: (a) car (b) monkey (c) deer (d) horse (e) dog (f) bird (g) airplane (h) cat (i) truck (j) ship"
},
{
"from": "gpt",
"value": "(i) truck"
}
] |
vision_flan(filtered)
|
vision-flan_recipe-qa+visual_coherence+3220
|
[
{
"from": "human",
"value": "The given image contains 4 image choices numbered A through D. Select the least similar image among the gorup"
},
{
"from": "gpt",
"value": "The least similar image is D"
}
] |
vision_flan(filtered)
|
vision-flan_VisDA-2017+image_classification+src_3_2876__231_349_165
|
[
{
"from": "human",
"value": "Your task is to classify an image based on its corresponding object category. The image contains a variety of objects distributed among 12 categories, including aeroplane, horse, knife, person, plant, and others. To accurately classify the image, carefully analyze its visual characteristics, such as shape, color, texture, and spatial context relations, as these attributes can vary significantly across different domains. Once you have identified the object category of the image, output the appropriate label for your classification."
},
{
"from": "gpt",
"value": "truck"
}
] |
vision_flan(filtered)
|
vision-flan_ImageNet-R+image_domain_classification+painting_11
|
[
{
"from": "human",
"value": "Your goal is to classify the image based on its domain, which can be 'videogame', 'painting', 'sketch', 'cartoon', 'art', 'toy', 'deviantart', 'graphic', 'sculpture', 'misc', 'embroidery', 'sticker', 'graffiti', 'origami', or 'tattoo'. Your final output should specify the identified domain of the image."
},
{
"from": "gpt",
"value": "painting"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+elephant_image_category_classification+n02503517_3879-7.png
|
[
{
"from": "human",
"value": "You will be given an image of an elephant. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Cartoon (b) Art painting (c) Sketch (d) Photograph"
},
{
"from": "gpt",
"value": "(c) Sketch"
}
] |
vision_flan(filtered)
|
vision-flan_Places205+Image_env_classification+gsun_e791dd881dcf511ac0f0196cbcab1061
|
[
{
"from": "human",
"value": "In this task, you have to identify if the place or scene pictured is indoor or outdoor. In the image is among a total of 205 classes such as Hospital, Bridge, Courtyard, Motel,.... The classes of the images are a diverse set of places or scenes. Pay attention to the details as some of the images may contain an object that relates to a specific place while some images may directly show the place or scenary. So, your answer should be the place or scene shown in the image\nOptions: (a) Outdoor (b) Indoor"
},
{
"from": "gpt",
"value": "(a) Outdoor"
}
] |
vision_flan(filtered)
|
vision-flan_Places205+Image_env_classification+gsun_3449ad74900ab0bbf676ff29b43f9ed9
|
[
{
"from": "human",
"value": "In this task, you have to identify if the place or scene pictured is indoor or outdoor. In the image is among a total of 205 classes such as Hospital, Bridge, Courtyard, Motel,.... The classes of the images are a diverse set of places or scenes. Pay attention to the details as some of the images may contain an object that relates to a specific place while some images may directly show the place or scenary. So, your answer should be the place or scene shown in the image\nOptions: (a) Indoor (b) Outdoor"
},
{
"from": "gpt",
"value": "(b) Outdoor"
}
] |
vision_flan(filtered)
|
multiinstruct_VQAv2_116229000
|
[
{
"from": "human",
"value": "In this task, you are given the question \"Where is the parked vehicle?\" and you need to decide if the image provide you enough info to answer the question. \n\nOptions: (a) no (b) yes"
},
{
"from": "gpt",
"value": "(a) no"
}
] |
vision_flan(filtered)
|
vision-flan_Cars+car_classification+02655
|
[
{
"from": "human",
"value": "In this task, based on the given image dataset of different cars, you have to identify the model + car make + Year of Make of a car in the image among a total of 196 categories such as Audi A5 Coupe 2012, BMW 3 Series Sedan 2012, Bentley Arnage Sedan 2009,... Pay attention to details such as the size, logo, type of the car to identify the model. So by looking at a car image, Give your answer in the following format: Model of the Car++Make of the Car++Year of Make"
},
{
"from": "gpt",
"value": "BMW X5 SUV 2007"
}
] |
vision_flan(filtered)
|
vision-flan_VisDA-2017+object_classification_train_person_8933
|
[
{
"from": "human",
"value": "You are given an image which contains a 3D rendered object. Your goal is to identify the category of the object present in the image from the given options.\nOptions: (a) skateboard (b) aeroplane (c) horse (d) plant (e) car (f) bicycle (g) knife (h) person (i) truck (j) motorcycle"
},
{
"from": "gpt",
"value": "(h) person"
}
] |
vision_flan(filtered)
|
vision-flan_MVTecAD+image_classification+256
|
[
{
"from": "human",
"value": "Your objective is to classify an image based on its corresponding object category. The image provided encompasses a diverse range of industrial items, including a bottle, cable, carpet, and more. Focus on the overall visual appearance of the image, paying attention to details such as lines, shading, color scheme, and level of detail. It is crucial to analyze the distinctive characteristics of the object, such as its shape, color, and texture, as these features may vary significantly between different object categories. Once you have completed the classification process, output the appropriate object name based on your analysis."
},
{
"from": "gpt",
"value": "The object is a hazelnut."
}
] |
vision_flan(filtered)
|
vision-flan_DeepFashion_highres_Attribute_and_Category+Cloth_Classification+img_highres_subset_Quilted_Faux_Leather_Skirt-img_00000022.jpg
|
[
{
"from": "human",
"value": "Can you write a very short description of the cloth?"
},
{
"from": "gpt",
"value": "The cloth is a Quilted Faux Leather Skirt."
}
] |
vision_flan(filtered)
|
vision-flan_spot-the-diff+image_diff_identification+12133
|
[
{
"from": "human",
"value": "You are provided with an image which contains two pictures side by side. Your task is to identify the differences between the two pictures. Separate the differences with a comma."
},
{
"from": "gpt",
"value": "the man is gone, there is a girl on a bike, there are two girl near the store entrance"
}
] |
vision_flan(filtered)
|
vision-flan_PACS+dog_image_category_classification+pic_295.jpg
|
[
{
"from": "human",
"value": "You will be given an image of a dog. The image could be of different categories like painting, cartoon, photograph, or sketch. Identify the image category.\nOptions: (a) Sketch (b) Cartoon (c) Photograph (d) Art painting"
},
{
"from": "gpt",
"value": "(b) Cartoon"
}
] |
vision_flan(filtered)
|
vision-flan_FoodLogoDet-1500+food_logo_recognition+007314
|
[
{
"from": "human",
"value": "What is the logo in the image?"
},
{
"from": "gpt",
"value": "The logo in the image is Blue Diamond Almonds."
}
] |
vision_flan(filtered)
|
vision-flan_HICO+human_activity_detection+HICO_train2015_00035152.jpg
|
[
{
"from": "human",
"value": "Answer a simple question. What is the person in the image doing? If there is no action being performed, describe the main object in the image."
},
{
"from": "gpt",
"value": "A person is throwing the sports ball."
}
] |
vision_flan(filtered)
|
vision-flan_DeepFashion_highres_Attribute_and_Category+Cloth_Classification+img_highres_subset_Belted_Paisley_Print_Romper-img_00000030.jpg
|
[
{
"from": "human",
"value": "Can you write a very short description of the cloth?"
},
{
"from": "gpt",
"value": "The cloth is a Belted Paisley Print Romper."
}
] |
vision_flan(filtered)
|
vision-flan_cinic-10+image_classification_animal+132748
|
[
{
"from": "human",
"value": "The given image can contain various types of animals. Some of these animals are found in forests, drylands, or other natural areas. Some of them could also be domesticated pets. Please identify the animal in the picture."
},
{
"from": "gpt",
"value": "The image contains a deer"
}
] |
vision_flan(filtered)
|
vision-flan_Office_31+Image_Classification_ObjectAndCategory_amazon_file_cabinet_frame_0017.jpg
|
[
{
"from": "human",
"value": "The input for this task is an image of the commonly encountered office objects such as keyboards, file cabinets, and laptops from three different categories(AMAZON, DSLR, WEBCAM). The output of this task is to name the domain of image(AMAZON, DSLR, or WEBCAM) as well as the object in the image in the following format: 'Category ObjectName' (exp. amazon mug) AMAZON: these images were captured from a website of online merchants, they are captured against clean background. DSLR cameras offer improved image quality when compared to standard webcams."
},
{
"from": "gpt",
"value": "amazon file_cabinet"
}
] |
vision_flan(filtered)
|
vision-flan_spot-the-diff+image_diff_identification+10237
|
[
{
"from": "human",
"value": "You are provided with an image which contains two pictures side by side. Your task is to identify the differences between the two pictures. Separate the differences with a comma."
},
{
"from": "gpt",
"value": "the person next to the truck is not there anymore, the person walking is not there anymore"
}
] |
vision_flan(filtered)
|
vision-flan_VOC2007+object_detection+007595.jpg
|
[
{
"from": "human",
"value": "Identify some objects that are present in the image. Give a comma separated list as the output."
},
{
"from": "gpt",
"value": "person"
}
] |
vision_flan(filtered)
|
vision-flan_DeepFashion_highres_Attribute_and_Category+Cloth_Classification+img_highres_subset_Abstract_Print_Dolman_Top-img_00000042.jpg
|
[
{
"from": "human",
"value": "Can you write a very short description of the cloth?"
},
{
"from": "gpt",
"value": "The cloth is a Abstract Print Dolman Top."
}
] |
vision_flan(filtered)
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.