{"url":"/dataset/whoops","name":"WHOOPS!","full_name":null,"description_markdown":"WHOOPS! Is a dataset and benchmark for visual commonsense. The dataset is comprised of purposefully commonsense-defying images created by designers using publicly-available image generation tools like Midjourney. It contains commonsense-defying image from a wide range of reasons, deviations from expected social norms and everyday knowledge.","description_withheld":null,"homepage":"https://whoops-benchmark.github.io/","introduced_date":"2023-03-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/breaking-common-sense-whoops-a-vision-and","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","first_author":"Nitzan Bitton-Guetta","url":null},"license":{"name":"CC-By 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"},{"name":"Image-to-Text Retrieval","url":"/task/image-to-text-retrieval","datasets_with_task":"/datasets/task/image-to-text-retrieval"},{"name":"Visual Commonsense Reasoning","url":"/task/visual-commonsense-reasoning","datasets_with_task":"/datasets/task/visual-commonsense-reasoning"},{"name":"Explanation Generation","url":"/task/explanation-generation","datasets_with_task":"/datasets/task/explanation-generation"},{"name":"Visual Commonsense Tests","url":"/task/visual-commonsense-tests","datasets_with_task":"/datasets/task/visual-commonsense-tests"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WHOOPS!"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nitzanguetta/whoops_new_format","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nlphuji/whoops","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/explanation-generation-on-whoops","task":"Explanation Generation","dataset_variant":"WHOOPS!","rows":7,"metrics":["Human (%)","Accuracy"],"first_row_in_archive_order":{"model":"Ground-truth Caption -> GPT3 (Oracle)","paper":"/paper/breaking-common-sense-whoops-a-vision-and","metrics":{"Human (%)":"68"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-to-text-retrieval-on-whoops","task":"Image-to-Text Retrieval","dataset_variant":"WHOOPS!","rows":7,"metrics":["Specificity"],"first_row_in_archive_order":{"model":"BLIP2 FlanT5-XXL (Text-only FT)","paper":"/paper/breaking-common-sense-whoops-a-vision-and","metrics":{"Specificity":"94"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-whoops","task":"Image Captioning","dataset_variant":"WHOOPS!","rows":6,"metrics":["BLEU-4","CIDEr"],"first_row_in_archive_order":{"model":"BLIP2 FlanT5-XXL (Fine-tuned)","paper":"/paper/breaking-common-sense-whoops-a-vision-and","metrics":{"BLEU-4":"42","CIDEr":"177"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-vqa-on-whoops","task":"Visual Question Answering (VQA)","dataset_variant":"WHOOPS!","rows":6,"metrics":["Exact Match","BEM"],"first_row_in_archive_order":{"model":"BLIP2 FlanT5-XXL (Fine-tuned)","paper":"/paper/breaking-common-sense-whoops-a-vision-and","metrics":{"BEM":"57","Exact Match":"21"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vlis-unimodal-language-models-guide","title":"VLIS: Unimodal Language Models Guide Multimodal Language Generation","date":"2023-10-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/breaking-common-sense-whoops-a-vision-and","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","date":"2023-03-13","rows_on_this_dataset":24,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}