{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interactive-spatiotemporal-token-attention","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","arxiv_id":"2307.07469","date":"2023-07-14","proceeding":null,"authors":["Yuhang Wen","Zixuan Tang","Yunsheng Pang","Beichen Ding","Mengyuan Liu"],"abstract":"Recognizing interactive action plays an important role in human-robot interaction and collaboration. Previous methods use late fusion and co-attention mechanism to capture interactive relations, which have limited learning capability or inefficiency to adapt to more interacting entities. With assumption that priors of each entity are already known, they also lack evaluations on a more general setting addressing the diversity of subjects. To address these problems, we propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Specifically, our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. By extending the entity dimension, ISTs provide better interactive representations. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations. When modeling correlations, a strict entity ordering is usually irrelevant for recognizing interactive actions. To this end, Entity Rearrangement is proposed to eliminate the orderliness in ISTs for interchangeable entities. Extensive experiments on four datasets verify the effectiveness of ISTA-Net by outperforming state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/ISTA-Net","url_abs":"https://arxiv.org/abs/2307.07469v1","url_pdf":"https://arxiv.org/pdf/2307.07469v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"interactive-spatiotemporal-token-attention","repo_url":"https://github.com/Necolizer/ISTA-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-action-recognition","task_name":"3D Action Recognition"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"human-interaction-recognition","task_name":"Human Interaction Recognition"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-action-recognition-on-assembly101","task":"3D Action Recognition","dataset":"Assembly101","model":"ISTA-Net","rank_in_archive_order":5,"of":7,"metrics":{"Actions Top-1":"28.07","Object Top-1":"31.69","Verbs Top-1":"62.66"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-h2o-2-hands-and-objects","task":"Action Recognition","dataset":"H2O  (2 Hands and Objects)","model":"ISTA-Net","rank_in_archive_order":5,"of":11,"metrics":{"Actions Top-1":"89.09","Hand Pose":"3D","Object Label":"No","Object Pose":"Yes","RGB":"No"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d-1","task":"Human Interaction Recognition","dataset":"NTU RGB+D 120","model":"ISTA-Net","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy (Cross-Setup)":"91.7","Accuracy (Cross-Subject)":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-sbu","task":"Human Interaction Recognition","dataset":"SBU / SBU-Refine","model":"ISTA-Net","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"98.51±1.47"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-h2o-2","task":"Skeleton Based Action Recognition","dataset":"H2O  (2 Hands and Objects)","model":"ISTA-Net","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"89.09±1.21"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.07469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07469"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Necolizer/ISTA-Net","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7d0ad89a26a54179","entry":"window_partition","repo":"Necolizer/ISTA-Net","repo_kind":"official","path":"model/ISTANet.py","file_url":"https://github.com/Necolizer/ISTA-Net/blob/HEAD/model/ISTANet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d0ad89a26a54179"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}