{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:20:21Z","timestamp":1730254821106,"version":"3.28.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412111","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"4252-4259","source":"Crossref","is-referenced-by-count":0,"title":["Text Synopsis Generation for Egocentric Videos"],"prefix":"10.1109","author":[{"given":"Aidean","family":"Sharghi","sequence":"first","affiliation":[]},{"given":"Niels","family":"da Vitoria Lobo","sequence":"additional","affiliation":[]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1410","article-title":"Supervised sentence fusion with single-stage inference","author":"thadani","year":"0","journal-title":"Proceedings of the Sixth International Joint Conference on Natural Language Processing"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref33","first-page":"435","article-title":"Making a long video short: Dynamic video synopsis","volume":"1","author":"rav-acha","year":"0","journal-title":"2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR‘06)"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1162\/089120102762671927","article-title":"Introduction to the special issue on summarization","volume":"28","author":"radev","year":"2002","journal-title":"Computational Linguistics"},{"key":"ref31","first-page":"5005","article-title":"Learning deep structure-preserving image-text embeddings","author":"wang","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref30","first-page":"5781","article-title":"Enhancing video summarization via vision-language embedding","author":"plummer","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref37","first-page":"5179","article-title":"Tvsum: Summarizing web videos using titles","author":"song","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_32"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.115"},{"key":"ref34","first-page":"433","article-title":"Translating video content to natural language descriptions","author":"rohrbach","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1084"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref1","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1463563.1463590"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0794-5"},{"key":"ref21","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"0","journal-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47979-1_27"},{"key":"ref23","first-page":"2017","article-title":"Rouge: A package for automatic evaluation of summaries ACL","author":"lin","year":"0","journal-title":"Proceedings of Workshop on Text Summarization Branches Out Post Conference Workshop of ACL"},{"key":"ref26","first-page":"557","article-title":"A study of global inference algorithms in multi-document summarization","author":"mcdonald","year":"2007","journal-title":"European Conference on Information Retrieval"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref50","first-page":"766","article-title":"Video summarization with long short-term memory","author":"zhang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.322"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/321510.321519"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141967"},{"key":"ref13","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","author":"gong","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref15","first-page":"505","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.538"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref19","first-page":"1266","article-title":"A unified framework for event summarization and rare event detection","author":"kwon","year":"0","journal-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1046"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1409"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","article-title":"VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method","volume":"32","author":"de avila","year":"2011","journal-title":"Pattern Recognition Letters"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref9","first-page":"3059","article-title":"Weakly supervised dense event captioning in videos","author":"duan","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref47","article-title":"Videoset: Video summary evaluation through text","author":"yeung","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543588"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref44","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_19"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412111.pdf?arnumber=9412111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:48Z","timestamp":1652197248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412111\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412111","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}