{"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/hierarchical-deep-temporal-models-for-group","title":"Hierarchical Deep Temporal Models for Group Activity Recognition","arxiv_id":"1607.02643","date":"2016-07-09","proceeding":null,"authors":["Mostafa S. Ibrahim","Srikanth Muralidharan","Zhiwei Deng","Arash Vahdat","Greg Mori"],"abstract":"In this paper we present an approach for classifying the activity performed\nby a group of people in a video sequence. This problem of group activity\nrecognition can be addressed by examining individual person actions and their\nrelations. Temporal dynamics exist both at the level of individual person\nactions as well as at the level of group activity. Given a video sequence as\ninput, methods can be developed to capture these dynamics at both person-level\nand group-level detail. We build a deep model to capture these dynamics based\non LSTM (long short-term memory) models. In order to model both person-level\nand group-level dynamics, we present a 2-stage deep temporal model for the\ngroup activity recognition problem. In our approach, one LSTM model is designed\nto represent action dynamics of individual people in a video sequence and\nanother LSTM model is designed to aggregate person-level information for group\nactivity recognition. We collected a new dataset consisting of volleyball\nvideos labeled with individual and group activities in order to evaluate our\nmethod. Experimental results on this new Volleyball Dataset and the standard\nbenchmark Collective Activity Dataset demonstrate the efficacy of the proposed\nmodels.","url_abs":"http://arxiv.org/abs/1607.02643v1","url_pdf":"http://arxiv.org/pdf/1607.02643v1.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":"hierarchical-deep-temporal-models-for-group","repo_url":"https://github.com/mostafa-saad/deep-activity-rec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"group-activity-recognition","task_name":"Group Activity Recognition"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.02643","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}