{"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/concurrence-aware-long-short-term-sub","title":"Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition","arxiv_id":"1706.00931","date":"2017-06-03","proceeding":null,"authors":["Xiangbo Shu","Jinhui Tang","Guo-Jun Qi","Yan Song","Zechao Li","Liyan Zhang"],"abstract":"Recently, Long Short-Term Memory (LSTM) has become a popular choice to model\nindividual dynamics for single-person action recognition due to its ability of\nmodeling the temporal information in various ranges of dynamic contexts.\nHowever, existing RNN models only focus on capturing the temporal dynamics of\nthe person-person interactions by naively combining the activity dynamics of\nindividuals or modeling them as a whole. This neglects the inter-related\ndynamics of how person-person interactions change over time. To this end, we\npropose a novel Concurrence-Aware Long Short-Term Sub-Memories (Co-LSTSM) to\nmodel the long-term inter-related dynamics between two interacting people on\nthe bounding boxes covering people. Specifically, for each frame, two\nsub-memory units store individual motion information, while a concurrent LSTM\nunit selectively integrates and stores inter-related motion information between\ninteracting people from these two sub-memory units via a new co-memory cell.\nExperimental results on the BIT and UT datasets show the superiority of\nCo-LSTSM compared with the state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1706.00931v1","url_pdf":"http://arxiv.org/pdf/1706.00931v1.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-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-interaction-recognition-on-bit","task":"Human Interaction Recognition","dataset":"BIT","model":"Co-LSTSM","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"92.88"},"uses_additional_data":false},{"leaderboard":"/sota/human-interaction-recognition-on-ut","task":"Human Interaction Recognition","dataset":"UT","model":"Co-LSTSM","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"95.00"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}