{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:24:04Z","timestamp":1778084644078,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747592","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"1650-1654","source":"Crossref","is-referenced-by-count":10,"title":["Exploiting Caption Diversity for Unsupervised Video Summarization"],"prefix":"10.1109","author":[{"given":"Michail","family":"Kaseris","sequence":"first","affiliation":[{"name":"Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Mademlis","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Pitas","sequence":"additional","affiliation":[{"name":"Aristotle University of Thessaloniki,Department of Informatics,Thessaloniki,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/9781601986290"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3347449.3357482"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_40"},{"key":"ref14","article-title":"Video summarization using Fully Convolutional sequence Networks","author":"rochan","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-13-2122-1","article-title":"Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward","author":"zhou","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref16","article-title":"Enhanced deep video summarization network","author":"gonuguntla","year":"2019","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00809"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2951680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2615289"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2016.7813397"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.12.020"},{"key":"ref5","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":"ref8","article-title":"TTH-RNN: Tensor-train hierarchical recurrent neural network for video summarization","author":"zhao","year":"2020","journal-title":"IEEE Transactions on Industrial Electronics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516997"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296356"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462274"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351056"},{"key":"ref22","article-title":"TV-Sum: Summarizing web videos using titles","author":"song","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref21","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref24","article-title":"Category-specific video summarization","author":"potapov","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506088"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747592.pdf?arnumber=9747592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:00Z","timestamp":1660594080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747592","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}