{"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/cern-confidence-energy-recurrent-network-for","title":"CERN: Confidence-Energy Recurrent Network for Group Activity Recognition","arxiv_id":"1704.03058","date":"2017-04-10","proceeding":"CVPR 2017 7","authors":["Tianmin Shu","Sinisa Todorovic","Song-Chun Zhu"],"abstract":"This work is about recognizing human activities occurring in videos at\ndistinct semantic levels, including individual actions, interactions, and group\nactivities. The recognition is realized using a two-level hierarchy of Long\nShort-Term Memory (LSTM) networks, forming a feed-forward deep architecture,\nwhich can be trained end-to-end. In comparison with existing architectures of\nLSTMs, we make two key contributions giving the name to our approach as\nConfidence-Energy Recurrent Network -- CERN. First, instead of using the common\nsoftmax layer for prediction, we specify a novel energy layer (EL) for\nestimating the energy of our predictions. Second, rather than finding the\ncommon minimum-energy class assignment, which may be numerically unstable under\nuncertainty, we specify that the EL additionally computes the p-values of the\nsolutions, and in this way estimates the most confident energy minimum. The\nevaluation on the Collective Activity and Volleyball datasets demonstrates: (i)\nadvantages of our two contributions relative to the common softmax and\nenergy-minimization formulations and (ii) a superior performance relative to\nthe state-of-the-art approaches.","url_abs":"http://arxiv.org/abs/1704.03058v1","url_pdf":"http://arxiv.org/pdf/1704.03058v1.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":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"group-activity-recognition","task_name":"Group Activity Recognition"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/group-activity-recognition-on-volleyball","task":"Group Activity Recognition","dataset":"Volleyball","model":"Shu et al.","rank_in_archive_order":12,"of":12,"metrics":{"Accuracy":"83.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.03058","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}