{"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/social-scene-understanding-end-to-end-multi","title":"Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition","arxiv_id":"1611.09078","date":"2016-11-28","proceeding":"CVPR 2017 7","authors":["Timur Bagautdinov","Alexandre Alahi","François Fleuret","Pascal Fua","Silvio Savarese"],"abstract":"We present a unified framework for understanding human social behaviors in\nraw image sequences. Our model jointly detects multiple individuals, infers\ntheir social actions, and estimates the collective actions with a single\nfeed-forward pass through a neural network. We propose a single architecture\nthat does not rely on external detection algorithms but rather is trained\nend-to-end to generate dense proposal maps that are refined via a novel\ninference scheme. The temporal consistency is handled via a person-level\nmatching Recurrent Neural Network. The complete model takes as input a sequence\nof frames and outputs detections along with the estimates of individual actions\nand collective activities. We demonstrate state-of-the-art performance of our\nalgorithm on multiple publicly available benchmarks.","url_abs":"http://arxiv.org/abs/1611.09078v1","url_pdf":"http://arxiv.org/pdf/1611.09078v1.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":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-volleyball","task":"Action Recognition","dataset":"Volleyball","model":"GTT (VGG19)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-volleyball","task":"Action Recognition","dataset":"Volleyball","model":"SSU (GT)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"81.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.09078","atlas_url":"https://app.syntology.ai/?focus=1611.09078","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}