{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:36:32Z","timestamp":1778081792538,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872256"],"award-info":[{"award-number":["61872256"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3416276","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:26:25Z","timestamp":1602505585000},"page":"4699-4702","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Person-level Action Recognition in Complex Events via TSD-TSM Networks"],"prefix":"10.1145","author":[{"given":"Yanbin","family":"Hao","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi-Niu","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_2_1","unstructured":"Rohit Girdhar Jo ao Carreira Carl Doersch and Andrew Zisserman. 2018. A better baseline for ava. arXiv preprint arXiv:1807.10066 (2018).  Rohit Girdhar Jo ao Carreira Carl Doersch and Andrew Zisserman. 2018. A better baseline for ava. arXiv preprint arXiv:1807.10066 (2018)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_6_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017).  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_2_8_1","volume-title":"Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events. arXiv preprint arXiv:2005.04490","author":"Lin Weiyao","year":"2020"},{"key":"e_1_3_2_2_9_1","unstructured":"Yu Liu Guanglu Song Yuhang Zang Yan Gao Enze Xie Junjie Yan Chen Change Loy and Xiaogang Wang. 2020. 1st Place Solutions for OpenImage2019--Object Detection and Instance Segmentation. arXiv preprint arXiv:2003.07557 (2020).  Yu Liu Guanglu Song Yuhang Zang Yan Gao Enze Xie Junjie Yan Chen Change Loy and Xiaogang Wang. 2020. 1st Place Solutions for OpenImage2019--Object Detection and Instance Segmentation. arXiv preprint arXiv:2003.07557 (2020)."},{"key":"e_1_3_2_2_10_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99."},{"key":"e_1_3_2_2_11_1","unstructured":"Shuai Shao Zijian Zhao Boxun Li Tete Xiao Gang Yu Xiangyu Zhang and Jian Sun. 2018. CrowdHuman: A Benchmark for Detecting Human in a Crowd. arXiv preprint arXiv:1805.00123 (2018).  Shuai Shao Zijian Zhao Boxun Li Tete Xiao Gang Yu Xiangyu Zhang and Jian Sun. 2018. CrowdHuman: A Benchmark for Detecting Human in a Crowd. arXiv preprint arXiv:1805.00123 (2018)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Guanglu Song Yu Liu and Xiaogang Wang. 2020. Revisiting the Sibling Head in Object Detector. CVPR (2020).  Guanglu Song Yu Liu and Xiaogang Wang. 2020. Revisiting the Sibling Head in Object Detector. CVPR (2020).","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.3169\/mta.4.218"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2884478"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3416276","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3416276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:24Z","timestamp":1750197684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3416276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":15,"alternative-id":["10.1145\/3394171.3416276","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3416276","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}