{"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/a-self-adaptive-proposal-model-for-temporal","title":"A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning","arxiv_id":"1706.07251","date":"2017-06-22","proceeding":null,"authors":["Jingjia Huang","Nannan Li","Tao Zhang","Ge Li"],"abstract":"Existing action detection algorithms usually generate action proposals\nthrough an extensive search over the video at multiple temporal scales, which\nbrings about huge computational overhead and deviates from the human perception\nprocedure. We argue that the process of detecting actions should be naturally\none of observation and refinement: observe the current window and refine the\nspan of attended window to cover true action regions. In this paper, we propose\nan active action proposal model that learns to find actions through\ncontinuously adjusting the temporal bounds in a self-adaptive way. The whole\nprocess can be deemed as an agent, which is firstly placed at a position in the\nvideo at random, adopts a sequence of transformations on the current attended\nregion to discover actions according to a learned policy. We utilize\nreinforcement learning, especially the Deep Q-learning algorithm to learn the\nagent's decision policy. In addition, we use temporal pooling operation to\nextract more effective feature representation for the long temporal window, and\ndesign a regression network to adjust the position offsets between predicted\nresults and the ground truth. Experiment results on THUMOS 2014 validate the\neffectiveness of the proposed approach, which can achieve competitive\nperformance with current action detection algorithms via much fewer proposals.","url_abs":"http://arxiv.org/abs/1706.07251v1","url_pdf":"http://arxiv.org/pdf/1706.07251v1.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":"a-self-adaptive-proposal-model-for-temporal","repo_url":"https://github.com/Parapompadoo/Temporal_Action_Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":null,"task_name":"Position"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}