{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T20:24:57Z","timestamp":1783110297379,"version":"3.54.6"},"reference-count":60,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3664996","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:48Z","timestamp":1771276068000},"page":"5254-5261","source":"Crossref","is-referenced-by-count":0,"title":["Long Video Understanding With Learnable Retrieval in Video-Language Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4081-736X","authenticated-orcid":false,"given":"Jiaqi","family":"Xu","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\/0000-0001-9145-9957","authenticated-orcid":false,"given":"Cuiling","family":"Lan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-7018","authenticated-orcid":false,"given":"Xuejin","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-6424","authenticated-orcid":false,"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref2","article-title":"ChatVideo: A tracklet-centric multimodal and versatile video understanding system","author":"Wang","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref5","article-title":"Video-RAG: Visually-aligned retrieval-augmented long video comprehension","author":"Luo","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1515\/9781400849482"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002667"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3333192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref16","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref17","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"ref20","first-page":"11888","article-title":"ViperGPT: Visual inference via python execution for reasoning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sur","year":"2023"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref23","first-page":"9460","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ye","year":"2023"},{"key":"ref24","first-page":"453","article-title":"LongVLM: Efficient long video understanding via large language models","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Weng","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref28","article-title":"EALD-MLLM: Emotion analysis in long-sequential and de-identity videos with multi-modal large language model","author":"Li","year":"2024"},{"key":"ref29","first-page":"186","article-title":"ViLA: Efficient video-language alignment for video question answering","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lin","year":"2024"},{"key":"ref30","article-title":"Semi-parametric video-grounded text generation","author":"Kim","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680826"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3792"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"key":"ref38","first-page":"5613","article-title":"In-the-wild video question answering","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Castro","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00162"},{"key":"ref40","first-page":"4352","article-title":"LifeQA: A real-life dataset for video question answering","volume-title":"Proc. 25th Lang. Resour. Eval. Conf.","author":"Castro","year":"2020"},{"key":"ref41","article-title":"Social-IQ 2.0 challenge: Benchmarking multimodal social understanding","author":"Wilf","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0010"},{"key":"ref43","article-title":"LLaMA-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref48","first-page":"3362","article-title":"MiniGPT4-video: Advancing multimodal LLMs for video understanding with interleaved visual-textual tokens","volume-title":"Proc. 32nd ACM Int. Conf. Multimedia","author":"Ataallah","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref50","first-page":"16520","article-title":"InternVideo: General video foundation models via generative and discriminative learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Wang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref55","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref57","first-page":"15579","article-title":"Understanding long videos with multimodal language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ranasinghe","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11397184.pdf?arnumber=11397184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:53:32Z","timestamp":1783108412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3664996","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}