{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:06:38Z","timestamp":1757541998352,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548105","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:12Z","timestamp":1665416592000},"page":"790-798","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-Level Spatiotemporal Network for Video Summarization"],"prefix":"10.1145","author":[{"given":"Ming","family":"Yao","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Bai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Du","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuejun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Quan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuli","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Kang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413632"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM52913.2021.00045"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901741"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00085"},{"key":"e_1_3_2_2_7_1","volume-title":"Asian Conference on Computer Vision. Springer, 39--54","author":"Fajtl Jiri","year":"2018","unstructured":"Jiri Fajtl , Hajar Sadeghi Sokeh , Vasileios Argyriou , Dorothy Monekosso , and Paolo Remagnino . 2018 . Summarizing videos with attention . In Asian Conference on Computer Vision. Springer, 39--54 . Jiri Fajtl, Hajar Sadeghi Sokeh, Vasileios Argyriou, Dorothy Monekosso, and Paolo Remagnino. 2018. Summarizing videos with attention. In Asian Conference on Computer Vision. Springer, 39--54."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240651"},{"key":"e_1_3_2_2_9_1","volume-title":"Diverse sequential subset selection for supervised video summarization. Advances in neural information processing systems","author":"Gong Boqing","year":"2014","unstructured":"Boqing Gong , Wei-Lun Chao , Kristen Grauman , and Fei Sha . 2014. Diverse sequential subset selection for supervised video summarization. Advances in neural information processing systems , Vol. 27 ( 2014 ). Boqing Gong, Wei-Lun Chao, Kristen Grauman, and Fei Sha. 2014. Diverse sequential subset selection for supervised video summarization. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.132"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"e_1_3_2_2_14_1","volume-title":"Pacific-Rim Symposium on Image and Video Technology. Springer, 28--39","author":"Jiao Yifan","year":"2017","unstructured":"Yifan Jiao , Xiaoshan Yang , Tianzhu Zhang , Shucheng Huang , and Changsheng Xu . 2017 . Video highlight detection via deep ranking modeling . In Pacific-Rim Symposium on Image and Video Technology. Springer, 28--39 . Yifan Jiao, Xiaoshan Yang, Tianzhu Zhang, Shucheng Huang, and Changsheng Xu. 2017. Video highlight detection via deep ranking modeling. In Pacific-Rim Symposium on Image and Video Technology. Springer, 28--39."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018537"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.496"},{"key":"e_1_3_2_2_17_1","volume-title":"2012 IEEE conference on computer vision and pattern recognition. IEEE, 1346--1353","author":"Lee Yong Jae","year":"2012","unstructured":"Yong Jae Lee , Joydeep Ghosh , and Kristen Grauman . 2012 . Discovering important people and objects for egocentric video summarization . In 2012 IEEE conference on computer vision and pattern recognition. IEEE, 1346--1353 . Yong Jae Lee, Joydeep Ghosh, and Kristen Grauman. 2012. Discovering important people and objects for egocentric video summarization. In 2012 IEEE conference on computer vision and pattern recognition. IEEE, 1346--1353."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107677"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803639"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/354384.354443"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00174"},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 5179--5187","author":"Song Yale","year":"2015","unstructured":"Yale Song , Jordi Vallmitjana , Amanda Stent , and Alejandro Jaimes . 2015 . Tvsum: Summarizing web videos using titles . In Proceedings of the IEEE conference on computer vision and pattern recognition. 5179--5187 . Yale Song, Jordi Vallmitjana, Amanda Stent, and Alejandro Jaimes. 2015. Tvsum: Summarizing web videos using titles. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5179--5187."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2011.6012139"},{"key":"e_1_3_2_2_29_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","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. Advances in neural information processing systems , Vol. 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350992"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394263"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11297"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.514"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521352"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039886"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Lisboa Portugal","acronym":"MM '22"},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548105","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:19Z","timestamp":1750186819000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":41,"alternative-id":["10.1145\/3503161.3548105","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548105","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}