{"url":"/task/human-interaction-recognition","name":"Human Interaction Recognition","slug":"human-interaction-recognition","description_markdown":"Human Interaction Recognition (HIR) is a field of study that involves the development of computer algorithms to detect and recognize human interactions in videos, images, or other multimedia content. The goal of HIR is to automatically identify and analyze the social interactions between people, their body language, and facial expressions.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":22,"papers_with_code":8,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d-1","slug":"human-interaction-recognition-on-ntu-rgb-d-1","dataset":"NTU RGB+D 120","dataset_url":"/dataset/ntu-rgb-d-120","rows_in_archive":6,"metrics":["Accuracy (Cross-Setup)","Accuracy (Cross-Subject)"],"first_row_in_archive_order":{"model":"SkateFormer","paper_title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","paper_url":"/paper/skateformer-skeletal-temporal-transformer-for","paper_date":"2024-03-14","arxiv_id":"2403.09508","code_links":[{"title":"KAIST-VICLab/SkateFormer","url":"https://github.com/KAIST-VICLab/SkateFormer"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d","slug":"human-interaction-recognition-on-ntu-rgb-d","dataset":"NTU RGB+D","dataset_url":"/dataset/ntu-rgb-d","rows_in_archive":5,"metrics":["Accuracy (Cross-Subject)","Accuracy (Cross-View)"],"first_row_in_archive_order":{"model":"SkateFormer","paper_title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","paper_url":"/paper/skateformer-skeletal-temporal-transformer-for","paper_date":"2024-03-14","arxiv_id":"2403.09508","code_links":[{"title":"KAIST-VICLab/SkateFormer","url":"https://github.com/KAIST-VICLab/SkateFormer"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/human-interaction-recognition-on-ut","slug":"human-interaction-recognition-on-ut","dataset":"UT","dataset_url":null,"rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"H-LSTCM","paper_title":"Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition","paper_url":"/paper/hierarchical-long-short-term-concurrent","paper_date":"2018-11-01","arxiv_id":"1811.00270","code_links":[],"syntology":null}},{"leaderboard":"/sota/human-interaction-recognition-on-bit","slug":"human-interaction-recognition-on-bit","dataset":"BIT","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"H-LSTCM","paper_title":"Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition","paper_url":"/paper/hierarchical-long-short-term-concurrent","paper_date":"2018-11-01","arxiv_id":"1811.00270","code_links":[],"syntology":null}},{"leaderboard":"/sota/human-interaction-recognition-on-sbu","slug":"human-interaction-recognition-on-sbu","dataset":"SBU / SBU-Refine","dataset_url":"/dataset/sbu","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ISTA-Net","paper_title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","paper_url":"/paper/interactive-spatiotemporal-token-attention","paper_date":"2023-07-14","arxiv_id":"2307.07469","code_links":[{"title":"Necolizer/ISTA-Net","url":"https://github.com/Necolizer/ISTA-Net"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/human-interaction-recognition-on-epic-sounds","slug":"human-interaction-recognition-on-epic-sounds","dataset":"EPIC-SOUNDS","dataset_url":"/dataset/epic-sounds","rows_in_archive":1,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"Slow-Fast(Finetune by Fivewin team)","paper_title":"Slow-Fast Auditory Streams For Audio Recognition","paper_url":"/paper/slow-fast-auditory-streams-for-audio","paper_date":"2021-03-05","arxiv_id":"2103.03516","code_links":[{"title":"ekazakos/auditory-slow-fast","url":"https://github.com/ekazakos/auditory-slow-fast"},{"title":"porcelluscavia/audio-model","url":"https://github.com/porcelluscavia/audio-model"}],"syntology":null}},{"leaderboard":"/sota/human-interaction-recognition-on-sbu-1","slug":"human-interaction-recognition-on-sbu-1","dataset":"SBU","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LSTM-IRN'fc1inter+intra","paper_title":"Interaction Relational Network for Mutual Action Recognition","paper_url":"/paper/interaction-relational-network-for-mutual","paper_date":"2019-10-11","arxiv_id":"1910.04963","code_links":[{"title":"mauriciolp/inter-rel-net","url":"https://github.com/mauriciolp/inter-rel-net"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/human-interaction-recognition-on-ut-1","slug":"human-interaction-recognition-on-ut-1","dataset":"UT-Interaction","dataset_url":"/dataset/ut-interaction","rows_in_archive":1,"metrics":["Accuracy (Set 1)","Accuracy (Set 2)"],"first_row_in_archive_order":{"model":"LSTM-IRN'fc1inter+intra","paper_title":"Interaction Relational Network for Mutual Action Recognition","paper_url":"/paper/interaction-relational-network-for-mutual","paper_date":"2019-10-11","arxiv_id":"1910.04963","code_links":[{"title":"mauriciolp/inter-rel-net","url":"https://github.com/mauriciolp/inter-rel-net"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/ntu-rgb-d","name":"NTU RGB+D","full_name":"","num_papers_in_archive":476},{"url":"/dataset/ntu-rgb-d-120","name":"NTU RGB+D 120","full_name":"","num_papers_in_archive":137},{"url":"/dataset/sbu","name":"SBU / SBU-Refine","full_name":"SBU-Kinect-Interaction dataset v2.0","num_papers_in_archive":28},{"url":"/dataset/ut-interaction","name":"UT-Interaction","full_name":"","num_papers_in_archive":21},{"url":"/dataset/epic-sounds","name":"EPIC-SOUNDS","full_name":"","num_papers_in_archive":12},{"url":"/dataset/h2o","name":"H2O","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nuisi-dataset","name":"NuiSI Dataset","full_name":"Nuitrack Skeleton Interaction Dataset","num_papers_in_archive":1},{"url":"/dataset/h2o-interaction","name":"H²O Interaction","full_name":"Human-to-Human-or-Object Interaction","num_papers_in_archive":0}],"subtasks":[{"url":"/task/dense-contact-estimation","name":"Dense contact estimation"},{"url":"/task/mutual-gaze","name":"Mutual Gaze"},{"url":"/task/one-shot-3d-action-recognition","name":"One-Shot 3D Action Recognition"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":8,"of":8,"tagged_in_all":22,"items":[{"url":"/paper/slow-fast-auditory-streams-for-audio","title":"Slow-Fast Auditory Streams For Audio Recognition","date":"2021-03-05","arxiv_id":"2103.03516","repositories_listed":2,"syntology":null},{"url":"/paper/chase-learning-convex-hull-adaptive-shift-for","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","date":"2024-10-09","arxiv_id":"2410.07153","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/empathic-grounding-explorations-using","title":"Empathic Grounding: Explorations using Multimodal Interaction and Large Language Models with Conversational Agents","date":"2024-07-01","arxiv_id":"2407.01824","repositories_listed":1,"syntology":null},{"url":"/paper/skateformer-skeletal-temporal-transformer-for","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","date":"2024-03-14","arxiv_id":"2403.09508","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-mutual-excitation-for-hand-to-hand","title":"Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition","date":"2024-02-04","arxiv_id":"2402.02431","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/interactive-spatiotemporal-token-attention","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","date":"2023-07-14","arxiv_id":"2307.07469","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/two-person-graph-convolutional-network-for","title":"Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition","date":"2022-08-12","arxiv_id":"2208.06174","repositories_listed":1,"syntology":null},{"url":"/paper/interaction-relational-network-for-mutual","title":"Interaction Relational Network for Mutual Action Recognition","date":"2019-10-11","arxiv_id":"1910.04963","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}