{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T17:58:08Z","timestamp":1794333488140,"version":"4.9.0"},"reference-count":58,"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"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2024ZD01NL00101"],"award-info":[{"award-number":["2024ZD01NL00101"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02211","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23817-23827","source":"Crossref","is-referenced-by-count":6,"title":["Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow"],"prefix":"10.1109","author":[{"given":"Ruyang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangkun","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.52"},{"key":"ref2","article-title":"Physgame: Uncovering physical commonsense violations in gameplay videos","author":"Cao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"issue":"3","key":"ref7","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 %* chatgpt quality"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","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 arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2013.53"},{"key":"ref12","article-title":"Free video-llm: Prompt-guided visual perception for efficient training-free video 11 ms","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"Gpt-4v system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref16","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref24","article-title":"Kangaroo: A powerful video-language model supporting long-context video input","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref27","article-title":"Ppllava: Varied video sequence understanding with prompt guidance","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3796716"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref30","article-title":"Egoschema: A diagnostic benchmark for very longform video language understanding","volume":"36","author":"Mangalam","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref32","article-title":"Too many frames, not all useful: Efficient strategies for longform video qa","author":"Park","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1852"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref40","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","first-page":"186","article-title":"Vila: Efficient videolanguage alignment for video question answering","volume-title":"European Conference on Computer Vision","author":"Wang","year":"2024"},{"key":"ref42","article-title":"Retake: Reducing temporal and knowledge redundancy for long video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00311"},{"key":"ref46","first-page":"28828","article-title":"Longvideobench: A benchmark for long-context interleaved video-language understanding","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref48","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Slowfast-llava: A strong training-free baseline for video large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref53","article-title":"Flash-vstream: Memorybased real-time understanding for long video streams","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.30"},{"key":"ref56","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Mlvu: A comprehensive benchmark for multi-task long video understanding","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Apollo: An exploration of video understanding in large multimodal models","author":"Zohar","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11449020.pdf?arnumber=11449020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:27Z","timestamp":1777612527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02211","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}