{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:05Z","timestamp":1780949165178,"version":"3.54.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62404085"],"award-info":[{"award-number":["62404085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3698553","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:36:04Z","timestamp":1780342564000},"page":"83838-83851","source":"Crossref","is-referenced-by-count":0,"title":["Task-Driven Dual-Path Keyframe Selection: Enhancing Multimodal Video Understanding"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7131-6173","authenticated-orcid":false,"given":"Yurong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengwei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Intelligent Electrical Engineering and New Energy, Qingdao Hengxing University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deheng","family":"Su","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Silla University, Sasang-gu, Busan, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5850-1922","authenticated-orcid":false,"given":"Fengjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer, Jiangsu University of Science and Technology, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2185041"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3269951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-9423-3_47"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app132212520"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025774"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s26041239"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s25092677"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/systems10020031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3571119"},{"issue":"11","key":"ref11","first-page":"216","article-title":"Underground video semantic extraction and description generation technology based on multimodal large model","volume":"53","author":"Fu","year":"2025","journal-title":"Coal Sci. Technol."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i11.37896"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"ref14","article-title":"VQToken: Neural discrete token representation learning for extreme token reduction in video large language models","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685517"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2018.8516556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00218"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/sym17101737"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-006-0001-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058248"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"issue":"3s","key":"ref26","first-page":"1","article-title":"Deep learning for video summarization: A review","volume":"16","author":"Liu","year":"2020","journal-title":"ACM Trans. Multimedia Comput., Commun., Appl."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2532601"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11541017.pdf?arnumber=11541017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:56Z","timestamp":1780948376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11541017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3698553","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}