{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T19:34:16Z","timestamp":1785526456729,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":39,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3422839.3423064","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T08:38:46Z","timestamp":1602491926000},"page":"37-44","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Realistic Video Summarization through VISIOCITY"],"prefix":"10.1145","author":[{"given":"Vishal","family":"Kaushal","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Bombay, Mumbai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suraj","family":"Kothawade","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas, Dalas, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rishabh","family":"Iyer","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas, Dallas, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganesh","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay, Mumbai, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_40"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"e_1_3_2_1_3_1","volume-title":"Tools and techniques for video performance evaluation. In icpr","author":"Doermann David","unstructured":"David Doermann and David Mihalcik . 2000. Tools and techniques for video performance evaluation. In icpr . IEEE , 4167. David Doermann and David Mihalcik. 2000. Tools and techniques for video performance evaluation. In icpr. IEEE, 4167."},{"key":"e_1_3_2_1_4_1","volume-title":"Summarizing Videos with Attention. In 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_1_5_1","volume-title":"Video highlight prediction using audience chat reactions. arXiv preprint arXiv:1707.08559","author":"Fu Cheng-Yang","year":"2017","unstructured":"Cheng-Yang Fu , Joon Lee , Mohit Bansal , and Alexander C Berg . 2017. Video highlight prediction using audience chat reactions. arXiv preprint arXiv:1707.08559 ( 2017 ). Cheng-Yang Fu, Joon Lee, Mohit Bansal, and Alexander C Berg. 2017. Video highlight prediction using audience chat reactions. arXiv preprint arXiv:1707.08559 (2017)."},{"key":"e_1_3_2_1_6_1","volume-title":"Attentive and Adversarial Learning for Video Summarization. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 1579--1587","author":"Fu Tsu-Jui","year":"2019","unstructured":"Tsu-Jui Fu , Shao-Heng Tai , and Hwann-Tzong Chen . 2019 . Attentive and Adversarial Learning for Video Summarization. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 1579--1587 . Tsu-Jui Fu, Shao-Heng Tai, and Hwann-Tzong Chen. 2019. Attentive and Adversarial Learning for Video Summarization. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 1579--1587."},{"key":"e_1_3_2_1_7_1","unstructured":"Boqing Gong Wei-Lun Chao Kristen Grauman and Fei Sha. 2014. Diverse sequential subset selection for supervised video summarization. In Advances in Neural Information Processing Systems. 2069--2077.  Boqing Gong Wei-Lun Chao Kristen Grauman and Fei Sha. 2014. Diverse sequential subset selection for supervised video summarization. In Advances in Neural Information Processing Systems. 2069--2077."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Michael Gygli Helmut Grabner Hayko Riemenschneider and Luc Van Gool. 2014a. Creating Summaries from User Videos. In ECCV .  Michael Gygli Helmut Grabner Hayko Riemenschneider and Luc Van Gool. 2014a. Creating Summaries from User Videos. In ECCV .","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"e_1_3_2_1_12_1","volume-title":"Video summarization with attention-based encoder-decoder networks","author":"Ji Zhong","year":"2019","unstructured":"Zhong Ji , Kailin Xiong , Yanwei Pang , and Xuelong Li. 2019. Video summarization with attention-based encoder-decoder networks . IEEE Transactions on Circuits and Systems for Video Technology ( 2019 ). Zhong Ji, Kailin Xiong, Yanwei Pang, and Xuelong Li. 2019. Video summarization with attention-based encoder-decoder networks. IEEE Transactions on Circuits and Systems for Video Technology (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6772-0"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00076"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"e_1_3_2_1_16_1","volume-title":"Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. 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 Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 1346--1353 . Yong Jae Lee, Joydeep Ghosh, and Kristen Grauman. 2012. Discovering important people and objects for egocentric video summarization. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 1346--1353."},{"key":"e_1_3_2_1_17_1","volume-title":"FrameRank: A Text Processing Approach to Video Summarization. arXiv preprint arXiv:1904.05544","author":"Lei Zhuo","year":"2019","unstructured":"Zhuo Lei , Chao Zhang , Qian Zhang , and Guoping Qiu . 2019. FrameRank: A Text Processing Approach to Video Summarization. arXiv preprint arXiv:1904.05544 ( 2019 ). Zhuo Lei, Chao Zhang, Qian Zhang, and Guoping Qiu. 2019. FrameRank: A Text Processing Approach to Video Summarization. arXiv preprint arXiv:1904.05544 (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874095"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_10"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641116"},{"key":"e_1_3_2_1_22_1","volume-title":"Optimization Techniques","author":"Minoux Michel","unstructured":"Michel Minoux . 1978. Accelerated greedy algorithms for maximizing submodular set functions . In Optimization Techniques . Springer , 234--243. Michel Minoux. 1978. Accelerated greedy algorithms for maximizing submodular set functions. In Optimization Techniques . Springer, 234--243."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00778"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2708902"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.118"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_32"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.229"},{"key":"e_1_3_2_1_29_1","volume-title":"TVSum: Summarizing web videos using titles","author":"Song Yale","year":"2015","unstructured":"Yale Song , Jordi Vallmitjana , Amanda Stent , and Alejandro Jaimes . 2015a. TVSum: Summarizing web videos using titles .. In CVPR. IEEE Computer Society , 5179--5187. http:\/\/dblp.uni-trier.de\/db\/conf\/cvpr\/cvpr 2015 .html#SongVSJ15 Yale Song, Jordi Vallmitjana, Amanda Stent, and Alejandro Jaimes. 2015a. TVSum: Summarizing web videos using titles.. In CVPR. IEEE Computer Society, 5179--5187. http:\/\/dblp.uni-trier.de\/db\/conf\/cvpr\/cvpr2015.html#SongVSJ15"},{"key":"e_1_3_2_1_30_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 b. 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. 2015b. 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_1_31_1","volume-title":"Video abstraction: A systematic review and classification. ACM transactions on multimedia computing, communications, and applications (TOMM)","author":"Truong Ba Tu","year":"2007","unstructured":"Ba Tu Truong and Svetha Venkatesh . 2007. Video abstraction: A systematic review and classification. ACM transactions on multimedia computing, communications, and applications (TOMM) , Vol. 3 , 1 ( 2007 ), 3. Ba Tu Truong and Svetha Venkatesh. 2007. Video abstraction: A systematic review and classification. ACM transactions on multimedia computing, communications, and applications (TOMM) , Vol. 3, 1 (2007), 3."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123297"},{"key":"e_1_3_2_1_33_1","volume-title":"Convolutional Hierarchical Attention Network for Query-Focused Video Summarization. arXiv preprint arXiv:2002.03740","author":"Xiao Shuwen","year":"2020","unstructured":"Shuwen Xiao , Zhou Zhao , Zijian Zhang , Xiaohui Yan , and Min Yang . 2020. Convolutional Hierarchical Attention Network for Query-Focused Video Summarization. arXiv preprint arXiv:2002.03740 ( 2020 ). Shuwen Xiao, Zhou Zhao, Zijian Zhang, Xiaohui Yan, and Min Yang. 2020. Convolutional Hierarchical Attention Network for Query-Focused Video Summarization. arXiv preprint arXiv:2002.03740 (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"e_1_3_2_1_35_1","volume-title":"Videoset: Video summary evaluation through text. arXiv preprint arXiv:1406.5824","author":"Yeung Serena","year":"2014","unstructured":"Serena Yeung , Alireza Fathi , and Li Fei-Fei . 2014 . Videoset: Video summary evaluation through text. arXiv preprint arXiv:1406.5824 (2014). Serena Yeung, Alireza Fathi, and Li Fei-Fei. 2014. Videoset: Video summary evaluation through text. arXiv preprint arXiv:1406.5824 (2014)."},{"key":"e_1_3_2_1_36_1","volume-title":"Ping Li, Li Zhou, and Jiashi Feng.","author":"Yuan Li","year":"2019","unstructured":"Li Yuan , Francis EH Tay , Ping Li, Li Zhou, and Jiashi Feng. 2019 . Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization . arXiv preprint arXiv:1904.08265 (2019). Li Yuan, Francis EH Tay, Ping Li, Li Zhou, and Jiashi Feng. 2019. Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization. arXiv preprint arXiv:1904.08265 (2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"e_1_3_2_1_39_1","unstructured":"Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495.  Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"}],"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 2nd International Workshop on AI for Smart TV Content Production, Access and Delivery"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3422839.3423064","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3422839.3423064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:56Z","timestamp":1750195496000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3422839.3423064"}},"subtitle":["A New Benchmark and Evaluation Framework"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":39,"alternative-id":["10.1145\/3422839.3423064","10.1145\/3422839"],"URL":"https:\/\/doi.org\/10.1145\/3422839.3423064","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"}}]}}