{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:46:56Z","timestamp":1785840416618,"version":"3.56.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302474"],"award-info":[{"award-number":["62302474"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3598709","type":"journal-article","created":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:44:32Z","timestamp":1755715472000},"page":"5369-5384","source":"Crossref","is-referenced-by-count":17,"title":["Improving Video Summarization by Exploring the Coherence Between Corresponding Captions"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4792-3576","authenticated-orcid":false,"given":"Cheng","family":"Ye","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2774-2875","authenticated-orcid":false,"given":"Weidong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3163855"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3416710"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3222623"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087514"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3182866"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190939"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00295"},{"key":"ref10","article-title":"IntentVizor: Towards generic query guided interactive video summarization using slow-fast graph convolutional networks","author":"Wu","year":"2021","journal-title":"arXiv:2109.14834"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746911"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02436"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364500"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28208"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01783"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428318"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.099"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109128"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443558"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21422"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29899"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3335875"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3514250"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02683"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01973"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681603"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3590937"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475534"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.100"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3546312"},{"key":"ref37","first-page":"13936","article-title":"A graph matching perspective with transformers on video instance segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qin"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3333206"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311447"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.25"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428330"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3530570"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395804"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3021980"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548406"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref49","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref50","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref51","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv:2001.04451"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"issue":"8","key":"ref54","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039886"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01590"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref62","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref63","article-title":"ERNIE-ViLG: Unified generative pre-training for bidirectional vision-language generation","author":"Zhang","year":"2021","journal-title":"arXiv:2112.15283"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref70","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00778"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_30"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3072117"},{"key":"ref74","first-page":"13988","article-title":"CLIP-it! Language-guided video summarization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Narasimhan"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186506"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275069"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143699"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2307\/2332303"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1201\/9780367802417"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018537"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_11"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1137"},{"key":"ref86","article-title":"VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv:2501.13106"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3070732"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11130654.pdf?arnumber=11130654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:33:30Z","timestamp":1756319610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3598709","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}