{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:34:17Z","timestamp":1767339257829,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST109-2221-E-005-063,MOST109-2314-B-006-024,MOST110-2327-B-006-006"],"award-info":[{"award-number":["MOST109-2221-E-005-063,MOST109-2314-B-006-024,MOST110-2327-B-006-006"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,25]]},"DOI":"10.23919\/mva51890.2021.9511350","type":"proceedings-article","created":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T20:20:28Z","timestamp":1629404428000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Video Summarization With Frame Index Vision Transformer"],"prefix":"10.23919","author":[{"given":"Tzu-Chun","family":"Hsu","sequence":"first","affiliation":[]},{"given":"Yi-Sheng","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Chun-Rong","family":"Huang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","first-page":"1","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"loshchilov","year":"0","journal-title":"Proc Int'l Conf Learning Representations"},{"key":"ref10","first-page":"1","article-title":"Di-verse sequential subset selection for supervised video summarization","volume":"27","author":"gong","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2904996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2001374"},{"key":"ref14","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proc Intl Conf Learning Representations"},{"key":"ref15","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref17","first-page":"104","article-title":"Automatic video summarization by graph modeling","volume":"1","author":"ngo","year":"0","journal-title":"Proc Int'l Conf Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21074-8_4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870832"},{"key":"ref27","first-page":"358","article-title":"Video summarization using fully convolutional sequence networks","author":"rochan","year":"0","journal-title":"Proc Euro Conf Computer Vision"},{"key":"ref3","first-page":"5179","article-title":"Tv-sum: Summarizing web videos using titles","author":"song","year":"0","journal-title":"Proc Conf Computer Vision and Pattern Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.29"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2308652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47979-1_26"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2308603"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.08.007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"ref1","first-page":"533","article-title":"A user attention model for video summarization","author":"yu-fei","year":"0","journal-title":"Proc ACM Conf Multimedia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref23","first-page":"2982","article-title":"Unsuper-vised video summarization with adversarial lstm networks","author":"mahasseni","year":"0","journal-title":"Proc Conf Computer Vision and Pattern Recognition"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039886"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889265"}],"event":{"name":"2021 17th International Conference on Machine Vision and Applications (MVA)","start":{"date-parts":[[2021,7,25]]},"location":"Aichi, Japan","end":{"date-parts":[[2021,7,27]]}},"container-title":["2021 17th International Conference on Machine Vision and Applications (MVA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9511254\/9511341\/09511350.pdf?arnumber=9511350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,22]],"date-time":"2021-11-22T21:13:35Z","timestamp":1637615615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9511350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,25]]},"references-count":30,"URL":"https:\/\/doi.org\/10.23919\/mva51890.2021.9511350","relation":{},"subject":[],"published":{"date-parts":[[2021,7,25]]}}}