{"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/igformer-interaction-graph-transformer-for","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","arxiv_id":"2207.12100","date":"2022-07-25","proceeding":null,"authors":["Yunsheng Pang","Qiuhong Ke","Hossein Rahmani","James Bailey","Jun Liu"],"abstract":"Human interaction recognition is very important in many applications. One crucial cue in recognizing an interaction is the interactive body parts. In this work, we propose a novel Interaction Graph Transformer (IGFormer) network for skeleton-based interaction recognition via modeling the interactive body parts as graphs. More specifically, the proposed IGFormer constructs interaction graphs according to the semantic and distance correlations between the interactive body parts, and enhances the representation of each person by aggregating the information of the interactive body parts based on the learned graphs. Furthermore, we propose a Semantic Partition Module to transform each human skeleton sequence into a Body-Part-Time sequence to better capture the spatial and temporal information of the skeleton sequence for learning the graphs. Extensive experiments on three benchmark datasets demonstrate that our model outperforms the state-of-the-art with a significant margin.","url_abs":"https://arxiv.org/abs/2207.12100v1","url_pdf":"https://arxiv.org/pdf/2207.12100v1.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":[],"tasks":[{"task_slug":"human-interaction-recognition","task_name":"Human Interaction Recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"graph-transformer","method_name":"Graph Transformer"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"lapeigen","method_name":"LapEigen"},{"method_slug":"laplacian-pe","method_name":"Laplacian PE"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d","task":"Human Interaction Recognition","dataset":"NTU RGB+D","model":"IGFormer","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy (Cross-Subject)":"93.6","Accuracy (Cross-View)":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d-1","task":"Human Interaction Recognition","dataset":"NTU RGB+D 120","model":"IGFormer","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy (Cross-Setup)":"86.5","Accuracy (Cross-Subject)":"85.4"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-sbu","task":"Human Interaction Recognition","dataset":"SBU / SBU-Refine","model":"IGFormer","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"98.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.12100","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}