{"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/chained-multi-stream-networks-exploiting-pose","title":"Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection","arxiv_id":"1704.00616","date":"2017-04-03","proceeding":"ICCV 2017 10","authors":["Mohammadreza Zolfaghari","Gabriel L. Oliveira","Nima Sedaghat","Thomas Brox"],"abstract":"General human action recognition requires understanding of various visual\ncues. In this paper, we propose a network architecture that computes and\nintegrates the most important visual cues for action recognition: pose, motion,\nand the raw images. For the integration, we introduce a Markov chain model\nwhich adds cues successively. The resulting approach is efficient and\napplicable to action classification as well as to spatial and temporal action\nlocalization. The two contributions clearly improve the performance over\nrespective baselines. The overall approach achieves state-of-the-art action\nclassification performance on HMDB51, J-HMDB and NTU RGB+D datasets. Moreover,\nit yields state-of-the-art spatio-temporal action localization results on\nUCF101 and J-HMDB.","url_abs":"http://arxiv.org/abs/1704.00616v2","url_pdf":"http://arxiv.org/pdf/1704.00616v2.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":"chained-multi-stream-networks-exploiting-pose","repo_url":"https://github.com/mzolfaghari/chained-multistream-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"spatio-temporal-action-localization","task_name":"Spatio-Temporal Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-j-hmdb","task":"Skeleton Based Action Recognition","dataset":"J-HMDB","model":"Chained (RGB+Flow +Pose)","rank_in_archive_order":6,"of":13,"metrics":{"Accuracy (RGB+pose)":"76.1","Accuracy (pose)":"56.8"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-jhmdb-2d","task":"Skeleton Based Action Recognition","dataset":"JHMDB (2D poses only)","model":"Chained","rank_in_archive_order":6,"of":6,"metrics":{"Average accuracy of 3 splits":"56.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.00616","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}