{"url":"/sota/human-object-interaction-anticipation-on","task":{"name":"Human-Object Interaction Anticipation","url":"/task/human-object-interaction-anticipation","note":null},"dataset":{"name":"VidHOI","url":"/dataset/vidhoi"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Human-Object Interaction (HOI) Anticipation is the task of predicting \"a set of interactions\" in a video that will happen in the future, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"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)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Person-wise Top5: t=1(mAP@0.5)":"higher","Person-wise Top5: t=3(mAP@0.5)":"higher","Person-wise Top5: t=5(mAP@0.5)":"higher"}},"counts":{"rows":3,"rows_with_code":2,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"HOI4ABOT","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"},"uses_additional_data":false,"paper_date":"2023-09-28","paper":"/paper/hoi4abot-human-object-interaction","paper_url":"https://arxiv.org/abs/2309.16524v2","paper_title":"HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"ST-GAZE","metrics":{"Person-wise Top5: t=1(mAP@0.5)":"37.59","Person-wise Top5: t=3(mAP@0.5)":"33.14","Person-wise Top5: t=5(mAP@0.5)":"32.75"},"uses_additional_data":false,"paper_date":"2023-06-06","paper":"/paper/human-object-interaction-prediction-in-videos","paper_url":"https://arxiv.org/abs/2306.03597v1","paper_title":"Human-Object Interaction Prediction in Videos through Gaze Following","code":"https://github.com/nizhf/hoi-prediction-gaze-transformer","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"STTRAN","metrics":{"Person-wise Top5: t=1(mAP@0.5)":"29.09","Person-wise Top5: t=3(mAP@0.5)":"27.59","Person-wise Top5: t=5(mAP@0.5)":"27.32"},"uses_additional_data":false,"paper_date":"2021-05-25","paper":"/paper/st-hoi-a-spatial-temporal-baseline-for-human","paper_url":"https://arxiv.org/abs/2105.11731v2","paper_title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","code":"https://github.com/coldmanck/VidHOI","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":4}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":4,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}