{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:13:31Z","timestamp":1782260011925,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425603"],"award-info":[{"award-number":["62425603"]}],"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":["62472208"],"award-info":[{"award-number":["62472208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20243018"],"award-info":[{"award-number":["BK20243018"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3653742","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:00:49Z","timestamp":1768338049000},"page":"5893-5908","source":"Crossref","is-referenced-by-count":3,"title":["VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding"],"prefix":"10.1109","volume":"36","author":[{"given":"Henghao","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7092-2877","authenticated-orcid":false,"given":"Ge-Peng","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University, Canberra, ACT, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0694-9458","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5401-7834","authenticated-orcid":false,"given":"Huan","family":"Xiong","sequence":"additional","affiliation":[{"name":"Institute for Advanced Study in Mathematics, Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref2","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3548845"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.559"},{"key":"ref15","article-title":"Grounding-prompter: Prompting LLM with multimodal information for temporal sentence grounding in long videos","author":"Chen","year":"2023","journal-title":"arXiv:2312.17117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref20","first-page":"41340","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Qian"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref22","first-page":"76749","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Lei"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref25","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref26","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3344097"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3211850"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3542081"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3510950"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.29"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref51","article-title":"Mem2Ego: Empowering vision-language models with global-to-ego memory for long-horizon embodied navigation","author":"Zhang","year":"2025","journal-title":"arXiv:2502.14254"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.4135\/9781446212967.n15"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref56","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref58","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref60","first-page":"60785","article-title":"VideoPrism: A foundational visual encoder for video understanding","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhao"},{"key":"ref61","article-title":"HawkEye: Training video-text LLMs for grounding text in videos","author":"Wang","year":"2024","journal-title":"arXiv:2403.10228"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref65","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3792"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_20"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02241"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11348931.pdf?arnumber=11348931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:55:32Z","timestamp":1778183732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11348931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":74,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3653742","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}