{"url":"/dataset/vidhoi","name":"VidHOI","full_name":null,"description_markdown":"VidHOI is a video-based human-object interaction detection benchmark. VidHOI is based on VidOR which is densely annotated with all humans and predefined objects showing up in each frame. VidOR is also more challenging as the videos are non-volunteering user-generated and thus jittery at times.\r\n\r\nImage source: [https://xdshang.github.io/docs/vidor.html](https://xdshang.github.io/docs/vidor.html)","description_withheld":null,"homepage":"https://github.com/coldmanck/VidHOI","introduced_date":"2021-05-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/st-hoi-a-spatial-temporal-baseline-for-human","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","first_author":"Meng-Jiun Chiou","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Detection","url":"/task/action-detection","datasets_with_task":"/datasets/task/action-detection"},{"name":"Human-Object Interaction Detection","url":"/task/human-object-interaction-detection","datasets_with_task":"/datasets/task/human-object-interaction-detection"},{"name":"Spatio-Temporal Action Localization","url":"/task/spatio-temporal-action-localization","datasets_with_task":"/datasets/task/spatio-temporal-action-localization"},{"name":"Human-Object Interaction Anticipation","url":"/task/human-object-interaction-anticipation","datasets_with_task":"/datasets/task/human-object-interaction-anticipation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VidHOI"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/human-object-interaction-anticipation-on","task":"Human-Object Interaction Anticipation","dataset_variant":"VidHOI","rows":3,"metrics":["Person-wise Top5: t=1(mAP@0.5)","Person-wise Top5: t=3(mAP@0.5)","Person-wise Top5: t=5(mAP@0.5)"],"first_row_in_archive_order":{"model":"HOI4ABOT","paper":"/paper/hoi4abot-human-object-interaction","metrics":{"Person-wise Top5: t=1(mAP@0.5)":"37.77","Person-wise Top5: t=3(mAP@0.5)":"34.75","Person-wise Top5: t=5(mAP@0.5)":"34.07"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/human-object-interaction-detection-on-vidhoi","task":"Human-Object Interaction Detection","dataset_variant":"VidHOI","rows":3,"metrics":["Detection: Full (mAP@0.5)","Detection: Non-Rare (mAP@0.5)","Detection: Rare (mAP@0.5)","Oracle: Full (mAP@0.5)","Oracle: Non-Rare (mAP@0.5)","Oracle: Rare (mAP@0.5)"],"first_row_in_archive_order":{"model":"HOI4ABOT","paper":"/paper/hoi4abot-human-object-interaction","metrics":{"Detection: Full (mAP@0.5)":"11.12","Detection: Non-Rare (mAP@0.5)":"18.48","Detection: Rare (mAP@0.5)":"5.61","Oracle: Full (mAP@0.5)":"40.37","Oracle: Non-Rare (mAP@0.5)":"54.52","Oracle: Rare (mAP@0.5)":"29.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/hoi4abot-human-object-interaction","title":"HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs","date":"2023-09-28","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/human-object-interaction-prediction-in-videos","title":"Human-Object Interaction Prediction in Videos through Gaze Following","date":"2023-06-06","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/st-hoi-a-spatial-temporal-baseline-for-human","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","date":"2021-05-25","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":4,"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":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":1,"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."}