{"url":"/dataset/egotaskqa","name":"EgoTaskQA","full_name":null,"description_markdown":"**EgoTask QA** benchmark contains 40K balanced question-answer pairs selected from 368K programmatically generated questions generated over 2K egocentric videos. It provides a single home for the crucial dimensions of task understanding through question-answering on real-world egocentric videos.\r\n\r\nSource: [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://arxiv.org/pdf/2210.03929.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.03929.pdf](https://arxiv.org/pdf/2210.03929.pdf)","description_withheld":null,"homepage":"https://sites.google.com/view/egotaskqa","introduced_date":"2022-10-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/egotaskqa-understanding-human-tasks-in","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","first_author":"Baoxiong Jia","url":null},"license":{"name":"CC BY-NC-SA","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EgoTaskQA"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-egotaskqa","task":"Question Answering","dataset_variant":"EgoTaskQA","rows":4,"metrics":["Direct"],"first_row_in_archive_order":{"model":"EgoVLPv2","paper":"/paper/egovlpv2-egocentric-video-language-pre","metrics":{"Direct":"46.26"},"code_links":[{"title":"facebookresearch/EgoVLPv2","url":"https://github.com/facebookresearch/EgoVLPv2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/glance-and-focus-memory-prompting-for-multi-1","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","date":"2024-01-03","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":9,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/egovlpv2-egocentric-video-language-pre","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","date":"2023-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":21,"samples_ran":12,"samples_unverified":9,"pointer_only_for_licence":2,"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."}