{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:57:16Z","timestamp":1784231836576,"version":"3.55.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFA1008501"],"award-info":[{"award-number":["2023YFA1008501"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2049"],"award-info":[{"award-number":["624B2049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2035"],"award-info":[{"award-number":["U22B2035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425101"],"award-info":[{"award-number":["62425101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502116"],"award-info":[{"award-number":["62502116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen KQTD","award":["20240729102051063"],"award-info":[{"award-number":["20240729102051063"]}]},{"name":"China Post-Doctoral Science Foundation","award":["2025M774315"],"award-info":[{"award-number":["2025M774315"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3633657","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:41:04Z","timestamp":1763404864000},"page":"3216-3232","source":"Crossref","is-referenced-by-count":9,"title":["Language-Guided Graph Representation Learning for Video Summarization"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-9016","authenticated-orcid":false,"given":"Wenrui","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8164-0700","authenticated-orcid":false,"given":"Hengyu","family":"Man","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of AI for Science, Shenzhen Graduate School, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6718"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01751"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3187288"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2557785"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2623699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940225"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355402"},{"key":"ref13","first-page":"13988","article-title":"Clip-it! language-guided video summarization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Narasimhan"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039886"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3072117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3335875"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186506"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695887"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107567"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327677"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112258"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110744"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112170"},{"key":"ref24","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Hong"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715202"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref27","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Gong"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.2979573"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00259"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247820"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-005-0129-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247852"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3477538"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.229"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00776"},{"key":"ref42","article-title":"VideoPoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref44","article-title":"VideoLLM: Modeling video sequence with large language models","author":"Chen","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393452"},{"key":"ref47","first-page":"13109","article-title":"Video-of-thought: Step-by-step video reasoning from perception to cognition","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Fei","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref49","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681464"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32374"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447504"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y"},{"key":"ref55","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref56","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref57","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref58","article-title":"Efficient representation learning using random walks for dynamic graphs","author":"Sajjad","year":"2019"},{"key":"ref59","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref60","first-page":"1204","article-title":"Graphnorm: A principled approach to accelerating graph neural network training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai"},{"key":"ref61","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/9780470191613"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22485-0_19"},{"key":"ref66","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref67","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1287\/opre.47.4.570"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12255"},{"key":"ref73","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gong"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.229"},{"key":"ref76","article-title":"Query-conditioned three-player adversarial network for video summarization","author":"Zhang","year":"2018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6929"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ISM52913.2021.00045"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01428"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11250802.pdf?arnumber=11250802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:06:15Z","timestamp":1770671175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11250802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":79,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3633657","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}