{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:19:19Z","timestamp":1770985159111,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222138","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T13:58:31Z","timestamp":1694440711000},"page":"1430-1434","source":"Crossref","is-referenced-by-count":8,"title":["Query-Based Video Summarization with Pseudo Label Supervision"],"prefix":"10.1109","author":[{"given":"Jia-Hong","family":"Huang","sequence":"first","affiliation":[{"name":"University of Amsterdam,Amsterdam,Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luka","family":"Murn","sequence":"additional","affiliation":[{"name":"BBC Research and Development,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marta","family":"Mrak","sequence":"additional","affiliation":[{"name":"BBC Research and Development,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcel","family":"Worring","sequence":"additional","affiliation":[{"name":"University of Amsterdam,Amsterdam,Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901741"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M1733"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859948"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01590"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350992"},{"key":"ref31","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref11","first-page":"766","article-title":"Video summarization with long short-term memory","author":"zhang","year":"2016","journal-title":"ECCV"},{"key":"ref33","first-page":"4243","article-title":"Analysis on noise reduction method for interferometric sar image","volume":"6","author":"zhi","year":"2004","journal-title":"IGARSS"},{"key":"ref10","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"ECCV"},{"key":"ref32","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv preprint arXiv 1706 03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390695"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123297"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2771247"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00262"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.395"},{"key":"ref18","article-title":"Video summarisation by classification with deep reinforcement learning","author":"zhou","year":"2018","journal-title":"arXiv 1807 03089"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00195"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref25","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1310 4546"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s20236941"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366583"},{"key":"ref28","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","volume":"27","author":"levy","year":"2014","journal-title":"NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1618"},{"key":"ref29","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref8","article-title":"Self-supervised learning for video correspondence flow","author":"lai","year":"2019","journal-title":"arXiv preprint arXiv 1905 00571"},{"key":"ref7","article-title":"Self-supervised learning by cross-modal audio-video clustering","author":"alwassel","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref4","first-page":"5179","article-title":"Tvsum: Summarizing web videos using titles","author":"song","year":"2015","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463662"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref5","first-page":"505","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"ECCV"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222138.pdf?arnumber=10222138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:26:43Z","timestamp":1701257203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222138","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}