{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T19:32:54Z","timestamp":1792870374011,"version":"4.5.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.00135","type":"proceedings-article","created":{"date-parts":[[2020,1,10]],"date-time":"2020-01-10T02:06:13Z","timestamp":1578621973000},"page":"1258-1267","source":"Crossref","is-referenced-by-count":116,"title":["Less Is More: Learning Highlight Detection From Video Duration"],"prefix":"10.1109","author":[{"given":"Bo","family":"Xiong","sequence":"first","affiliation":[{"name":"Univ. of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yannis","family":"Kalantidis","sequence":"additional","affiliation":[{"name":"Facebook Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepti","family":"Ghadiyaram","sequence":"additional","affiliation":[{"name":"Facebook"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[{"name":"Facebook AI Research &amp; UT Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref32","article-title":"Training convolutional networks with noisy labels","author":"sukhbaatar","year":"2014"},{"key":"ref31","article-title":"Tvsum: Summarizing web videos using titles","author":"song","year":"2015","journal-title":"CVPR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/354384.354443"},{"key":"ref37","article-title":"Highlights extraction from sports video based on an audio-visual marker detection framework","author":"xiong","year":"2005","journal-title":"ICME"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.514"},{"key":"ref35","article-title":"Sports highlight detection from keyword sequences using hmm","author":"wang","year":"2004","journal-title":"ICME"},{"key":"ref34","article-title":"Detecting highlights in sports videos: Cricket as a test case","author":"tang","year":"2011","journal-title":"ICME"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"2018","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.538"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.496"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref17","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"CVPR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref28","article-title":"Category-specific video summarization","author":"potapov","year":"2014","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.455"},{"key":"ref3","article-title":"Weakly-supervised video summarization using variational encoder-decoder and web prior","author":"cai","year":"2018","journal-title":"ECCV"},{"key":"ref6","article-title":"Diverse sequential subset selection for supervised video summarization","author":"gong","year":"2014","journal-title":"NIPS"},{"key":"ref29","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"reed","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref7","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"ECCV"},{"key":"ref2","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref22","article-title":"Exploring the limits of weakly supervised pretraining","author":"mahajan","year":"2018","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref42","article-title":"Video summarization with long short-term memory","author":"zhang","year":"2016","journal-title":"ECCV"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2012.11.020"},{"key":"ref41","article-title":"? svm for learning with label proportions","author":"yu","year":"2013","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.395"},{"key":"ref43","article-title":"Retrospective encoders for video summarization","author":"zhang","year":"2018","journal-title":"ECCV"},{"key":"ref25","article-title":"Learning with noisy labels","author":"natarajan","year":"2015","journal-title":"NIPS"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Long Beach, CA, USA","start":{"date-parts":[[2019,6,15]]},"end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08954030.pdf?arnumber=8954030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:04:23Z","timestamp":1660593863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8954030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2019.00135","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}