{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:10:08Z","timestamp":1750957808260,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T00:00:00Z","timestamp":1508371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["U1509206 U1611461 61625107"],"award-info":[{"award-number":["U1509206 U1611461 61625107"]}]},{"name":"Chinese Knowledge Center of Engineering Science and Technology"},{"name":"Qianjiang Talents Program of Zhejiang Province 2015"},{"name":"Key program of Zhejiang Province","award":["2015C01027"],"award-info":[{"award-number":["2015C01027"]}]},{"name":"973 program","award":["2015CB352302"],"award-info":[{"award-number":["2015CB352302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,19]]},"DOI":"10.1145\/3123266.3123362","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"1069-1077","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Detecting Temporal Proposal for Action Localization with Tree-structured Search Policy"],"prefix":"10.1145","author":[{"given":"Xinyang","family":"Jiang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Colombia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,10,19]]},"reference":[{"volume-title":"Hierarchical Object Detection with Deep Reinforcement Learning Deep Reinforcement Learning Workshop, NIPS.","year":"2016","author":"Bellver Miriam","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.414"},{"key":"e_1_3_2_1_4_1","unstructured":"jifeng dai Yi Li Kaiming He and Jian Sun. 2016. R-FCN: Object Detection via Region-based Fully Convolutional Networks Advances in Neural Information Processing Systems 29. 379--387. jifeng dai Yi Li Kaiming He and Jian Sun. 2016. R-FCN: Object Detection via Region-based Fully Convolutional Networks Advances in Neural Information Processing Systems 29. 379--387."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Georgia Gkioxari and Jitendra Malik. 2015. Finding action tubes Proceedings of the IEEE conference on computer vision and pattern recognition. 759--768. Georgia Gkioxari and Jitendra Malik. 2015. Finding action tubes Proceedings of the IEEE conference on computer vision and pattern recognition. 759--768.","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"F. C. Heilbron V. Escorcia B. Ghanem and J. C. Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 961--970. F. C. Heilbron V. Escorcia B. Ghanem and J. C. Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 961--970.","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"e_1_3_2_1_9_1","unstructured":"Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/crcv.ucf.edu\/THUMOS14\/. (2014). Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/crcv.ucf.edu\/THUMOS14\/. (2014)."},{"key":"e_1_3_2_1_10_1","unstructured":"Zequn Jie Xiaodan Liang Jiashi Feng Xiaojie Jin Wen Lu and Shuicheng Yan. 2016. Tree-Structured Reinforcement Learning for Sequential Object Localization Advances in Neural Information Processing Systems. 127--135. Zequn Jie Xiaodan Liang Jiashi Feng Xiaojie Jin Wen Lu and Shuicheng Yan. 2016. Tree-Structured Reinforcement Learning for Sequential Object Localization Advances in Neural Information Processing Systems. 127--135."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Stefan Mathe Aleksis Pirinen and Cristian Sminchisescu. 2016. Reinforcement learning for visual object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2894--2902. Stefan Mathe Aleksis Pirinen and Cristian Sminchisescu. 2016. Reinforcement learning for visual object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2894--2902.","DOI":"10.1109\/CVPR.2016.316"},{"volume-title":"et almbox","year":"2015","author":"Mnih Volodymyr","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"e_1_3_2_1_14_1","first-page":"91","article-title":"Faster R-CNN","volume":"28","author":"Ren Shaoqing","year":"2015","journal-title":"Towards Real-Time Object Detection with Region Proposal Networks Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Zheng Shou Dongang Wang and Shih-Fu Chang. 2016. Temporal action localization in untrimmed videos via multi-stage cnns Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1049--1058. Zheng Shou Dongang Wang and Shih-Fu Chang. 2016. Temporal action localization in untrimmed videos via multi-stage cnns Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1049--1058.","DOI":"10.1109\/CVPR.2016.119"},{"key":"e_1_3_2_1_16_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-Stream Convolutional Networks for Action Recognition in Videos. Advances in Neural Information Processing Systems 27. 568--576. Karen Simonyan and Andrew Zisserman. 2014. Two-Stream Convolutional Networks for Action Recognition in Videos. Advances in Neural Information Processing Systems 27. 568--576."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806226"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Zhongwen Xu Yi Yang and Alex G Hauptmann. 2015. A discriminative CNN video representation for event detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1798--1807. Zhongwen Xu Yi Yang and Alex G Hauptmann. 2015. A discriminative CNN video representation for event detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1798--1807.","DOI":"10.1109\/CVPR.2015.7298789"},{"volume-title":"2012 IEEE Conference on. 2296--2303","year":"2012","author":"Yang Jimei","key":"e_1_3_2_1_22_1"},{"volume-title":"Every moment counts: Dense detailed labeling of actions in complex videos. arXiv preprint arXiv:1507.05738","year":"2015","author":"Yeung Serena","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Serena Yeung Olga Russakovsky Greg Mori and Li Fei-Fei. 2016. End-to-end learning of action detection from frame glimpses in videos Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2678--2687. Serena Yeung Olga Russakovsky Greg Mori and Li Fei-Fei. 2016. End-to-end learning of action detection from frame glimpses in videos Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2678--2687.","DOI":"10.1109\/CVPR.2016.293"}],"event":{"name":"MM '17: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Mountain View California USA","acronym":"MM '17"},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123362","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T16:40:18Z","timestamp":1750956018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,19]]},"references-count":24,"alternative-id":["10.1145\/3123266.3123362","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123362","relation":{},"subject":[],"published":{"date-parts":[[2017,10,19]]},"assertion":[{"value":"2017-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}