{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:40Z","timestamp":1760245060722,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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\/501100007156","name":"Innovation and Technology Commission - Hong Kong","doi-asserted-by":"publisher","award":["ITS\/384\/18FX"],"award-info":[{"award-number":["ITS\/384\/18FX"]}],"id":[{"id":"10.13039\/501100007156","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\/3394171.3413595","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:27:35Z","timestamp":1602505655000},"page":"628-636","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Compact Bilinear Augmented Query Structured Attention for Sport Highlights Classification"],"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":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, 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"}]},{"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"DeepAIT (Hong Kong) Limited, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Hu","sequence":"additional","affiliation":[{"name":"DeepAIT (Hong Kong) Limited, 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","unstructured":"Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Paul Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. Youtube-8m: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016).  Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Paul Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. Youtube-8m: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_32"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 961--970","year":"2015","author":"Fabian Caba Heilbron Bernard Ghanem","key":"e_1_3_2_2_8_1"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2710635"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2038637"},{"key":"e_1_3_2_2_14_1","unstructured":"Yu-Gang Jiang Zuxuan Wu Jun Wang Xiangyang Xue and Shih-Fu Chang. [n.d.]. FCVID: Fudan-Columbia Video Dataset. ( [n. d.]).  Yu-Gang Jiang Zuxuan Wu Jun Wang Xiangyang Xue and Shih-Fu Chang. [n.d.]. FCVID: Fudan-Columbia Video Dataset. ( [n. d.])."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Andrej Karpathy George Toderici Sanketh Shetty Thomas Leung Rahul Sukthankar and Li Fei-Fei. 2014a. Large-scale Video Classification with Convolutional Neural Networks. In CVPR .  Andrej Karpathy George Toderici Sanketh Shetty Thomas Leung Rahul Sukthankar and Li Fei-Fei. 2014a. Large-scale Video Classification with Convolutional Neural Networks. In CVPR .","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_2_17_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_18_1","unstructured":"Jin-Hwa Kim Kyoung-Woon On Woosang Lim Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016. Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016).  Jin-Hwa Kim Kyoung-Woon On Woosang Lim Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016. Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325 (2016)."},{"key":"e_1_3_2_2_19_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"volume-title":"Proceedings of the International Conference on Computer Vision (ICCV) .","author":"Kuehne H.","key":"e_1_3_2_2_20_1"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12055"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.348"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"volume-title":"5th International Conference on Learning Representations, ICLR 2017 .","year":"2017","author":"Lin Zhouhan","key":"e_1_3_2_2_26_1"},{"key":"e_1_3_2_2_27_1","unstructured":"S. Maji J. Kannala E. Rahtu M. Blaschko and A. Vedaldi. 2013. Fine-Grained Visual Classification of Aircraft. Technical Report. arxiv: 1306.5151 [cs-cv]  S. Maji J. Kannala E. Rahtu M. Blaschko and A. Vedaldi. 2013. Fine-Grained Visual Classification of Aircraft. Technical Report. arxiv: 1306.5151 [cs-cv]"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Mathew Monfort Alex Andonian Bolei Zhou Kandan Ramakrishnan Sarah Adel Bargal Tom Yan Lisa Brown Quanfu Fan Dan Gutfreund Carl Vondrick et al. 2019. Moments in time dataset: one million videos for event understanding. IEEE transactions on pattern analysis and machine intelligence Vol. 42 2 (2019) 502--508.  Mathew Monfort Alex Andonian Bolei Zhou Kandan Ramakrishnan Sarah Adel Bargal Tom Yan Lisa Brown Quanfu Fan Dan Gutfreund Carl Vondrick et al. 2019. Moments in time dataset: one million videos for event understanding. IEEE transactions on pattern analysis and machine intelligence Vol. 42 2 (2019) 502--508.","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487591"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2616--2625","year":"2020","author":"Shao Dian","key":"e_1_3_2_2_31_1"},{"key":"e_1_3_2_2_32_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems. 568--576.  Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems. 568--576."},{"key":"e_1_3_2_2_33_1","unstructured":"Khurram Soomro Amir Roshan Zamir and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012).  Khurram Soomro Amir Roshan Zamir and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_35_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"volume-title":"Technical Report CNS-TR-2010-001. California Institute of Technology.","year":"2010","author":"Welinder P.","key":"e_1_3_2_2_38_1"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2884478"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Seattle WA USA","acronym":"MM '20"},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413595","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:14Z","timestamp":1750193234000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":42,"alternative-id":["10.1145\/3394171.3413595","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413595","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"}}]}}