{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:35Z","timestamp":1784179115696,"version":"3.55.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02131","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22958-22967","source":"Crossref","is-referenced-by-count":11,"title":["LVBench: An Extreme Long Video Understanding Benchmark"],"prefix":"10.1109","author":[{"given":"Weihan","family":"Wang","sequence":"first","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehai","family":"He","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyi","family":"Hong","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yean","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Qi","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Ding","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotao","family":"Gu","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiao","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Anthropic","year":"2024","journal-title":"The claude 3 model family: Opus, sonnet, haiku"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref9","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Seed1. 5-vl technical report","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01354"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref13","article-title":"Glm-4.1 v-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning","author":"Hong","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01263"},{"key":"ref16","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02095"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref20","article-title":"World model on million-length video and language with ringattention","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Kangaroo: A powerful video-language model supporting long-context video input","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref25","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref26","year":"2024","journal-title":"Gpt-4o"},{"key":"ref27","year":"2025","journal-title":"Gpt-4.1"},{"key":"ref28","article-title":"Mr. video: \u201cmapreduce\u201d is the principle for long video understanding","author":"Pang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1852"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref31","article-title":"Cinepile: A long video question answering dataset and benchmark","author":"Rawal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01725"},{"key":"ref35","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref37","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.283"},{"key":"ref40","article-title":"Longvideobench: A benchmark for long-context inter-leaved video-language understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref43","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"mplug-ow13: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref47","article-title":"Videollama 3: Frontier multi-modal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref49","article-title":"Movqa: A benchmark of versatile question-answering for long-form movie understanding","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443514.pdf?arnumber=11443514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:37Z","timestamp":1777613317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02131","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}