{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:30:05Z","timestamp":1774420205062,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889812","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion"],"prefix":"10.1109","author":[{"given":"Yaowei","family":"Guo","sequence":"first","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiazheng","family":"Xing","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Hou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Xin","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juntao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Demetri","family":"Terzopoulos","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenfanfu","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Video skimming: Taxonomy and comprehensive survey","author":"Sen","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3044600"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00297"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref8","first-page":"13 988","article-title":"CLIP-it! Language-guided video summarization","volume":"34","author":"Narasimhan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_31"},{"key":"ref10","article-title":"Multimodal frame-scoring transformer for video summarization","author":"Park","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3347318.3355524"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8297032"},{"key":"ref14","article-title":"Correlation-guided query-dependency calibration in video representation learning for temporal grounding","author":"Moon","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref24","article-title":"Probing visual-audio representation for video highlight detection via hard-pairs guided contrastive learning","author":"Li","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650814"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref29","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref31","article-title":"Qvhighlights: Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889812.pdf?arnumber=10889812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:27:01Z","timestamp":1774416421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889812","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}