{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:10Z","timestamp":1780949110542,"version":"3.54.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New Generation Artificial Intelligence-National Science and Technology Major Projection","award":["2025ZD0123100"],"award-info":[{"award-number":["2025ZD0123100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573399"],"award-info":[{"award-number":["62573399"]}],"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":["U25A20530"],"award-info":[{"award-number":["U25A20530"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3673141","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:36:39Z","timestamp":1773347799000},"page":"8694-8709","source":"Crossref","is-referenced-by-count":0,"title":["SELongVLM: Empowering Long Video Language Models With Self-Corrective Clip Selection"],"prefix":"10.1109","volume":"48","author":[{"given":"Kecheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-8313","authenticated-orcid":false,"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[{"name":"DBMI, HMS, Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0040-6177","authenticated-orcid":false,"given":"Mingfei","family":"Han","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0384-4392","authenticated-orcid":false,"given":"Haihong","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-7482","authenticated-orcid":false,"given":"Changlin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Medicine, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9642-8009","authenticated-orcid":false,"given":"Zhihui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"ref2","first-page":"13961","article-title":"MLVU: A comprehensive benchmark for multi-task long video understanding","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhou","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref4","article-title":"Tomato: Assessing visual temporal reasoning capabilities in multimodal foundation models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shangguan","year":"2025"},{"key":"ref5","article-title":"Longvideobench: A benchmark for long-context interleaved video-language understanding","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref8","article-title":"Videochat-flash: Hierarchical compression for long-context video modeling","author":"Li","year":"2024"},{"key":"ref9","article-title":"LongVU: Spatiotemporal adaptive compression for long video-language understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shen","year":"2025"},{"key":"ref10","article-title":"VideoLLM-mod: Efficient video-language streaming with mixture-of-depths vision computation","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref11","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024"},{"key":"ref12","article-title":"LongVila: Scaling long-context visual language models for long videos","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xue","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01279"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref17","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref18","first-page":"32076","article-title":"E.T. bench: Towards open-ended event-level video-language understanding","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref19","article-title":"Towards event-oriented long video understanding","author":"Du","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref21","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.","author":"Li","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref23","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref24","article-title":"PLLaVA: Parameter-free LLaVA extension from images to videos for video dense captioning","author":"Xu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref27","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref30","article-title":"LLaVA-next: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref34","article-title":"STAR: A benchmark for situated reasoning in real-world videos","author":"Wu","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1168"},{"key":"ref36","first-page":"24185","article-title":"INTERNVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Chen","year":"2024"},{"key":"ref37","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref38","article-title":"mPLUG-DocOwl: Modularized multimodal large language model for document understanding","author":"Ye","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref40","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs","author":"Tong","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref41","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023"},{"key":"ref42","article-title":"InternLM-XComposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"ref45","article-title":"Mixture-of-depths: Dynamically allocating compute in transformer-based language models","author":"Raposo","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01282"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00315"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"ref49","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref51","article-title":"Shot2story20 k: A new benchmark for comprehensive understanding of multi-shot videos","author":"Han","year":"2023"},{"key":"ref52","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"issue":"1","key":"ref53","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"NAACL-HLT"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref55","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref56","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref57","article-title":"Oryx MLLM: On-demand spatial-temporal understanding at arbitrary resolution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00360"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"ref60","article-title":"LLaVA-onevision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref61","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref62","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref63","article-title":"Hello GPT-4o","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref66","article-title":"Video-XL-2: Towards very long-video understanding through task-aware KV sparsification","author":"Qin","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref68","first-page":"81808","article-title":"Slowfocus: Enhancing fine-grained temporal understanding in video LLM","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Nie","year":"2024"},{"key":"ref69","article-title":"Video-XL-pro: Reconstructive token compression for extremely long video understanding","author":"Liu","year":"2025"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754839"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01882"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01876"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11430664.pdf?arnumber=11430664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:35Z","timestamp":1780948295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11430664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":74,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3673141","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":[[2026,7]]}}}