{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:38:56Z","timestamp":1776886736500,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096265","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["MHSCNET: A Multimodal Hierarchical Shot-Aware Convolutional Network for Video Summarization"],"prefix":"10.1109","author":[{"given":"Wujiang","family":"Xu","sequence":"first","affiliation":[{"name":"Ant Group,MYbank,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoshuai","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group,MYbank,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiongxu","family":"Ma","sequence":"additional","affiliation":[{"name":"Ant Group,MYbank,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ant Group,MYbank,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Ant Group,MYbank,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenfeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Institute of Information Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISM52913.2021.00045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref12","article-title":"Clip-it! language-guided video summarization","author":"narasimhan","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref15","article-title":"Video summarisation by classification with deep reinforcement learning","author":"zhou","year":"2018","journal-title":"arXiv preprint arXiv 1807 03089"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412057"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref11","article-title":"Audiovisual video summarization","author":"zhao","year":"2021","journal-title":"arXiv preprint arXiv 2105 07667"},{"key":"ref22","first-page":"5179","article-title":"Tv-sum: Summarizing web videos using titles","author":"song","year":"2015","journal-title":"CVPR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_39"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref17","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"iashin","year":"2020","journal-title":"arXiv preprint arXiv 2005 08068"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref19","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"arXiv preprint arXiv 1511 07122"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107677"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803639"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_11"},{"key":"ref4","first-page":"202","article-title":"Unsupervised video summarization with adversarial lstm networks","author":"mahasseni","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref6","first-page":"39","article-title":"Summarizing videos with attention","author":"fajtl","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351056"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096265.pdf?arnumber=10096265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:54:13Z","timestamp":1755906853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096265","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}