{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:38Z","timestamp":1777890218075,"version":"3.51.4"},"reference-count":45,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB3908503"],"award-info":[{"award-number":["2024YFB3908503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322608"],"award-info":[{"award-number":["62322608"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.02089","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22499-22508","source":"Crossref","is-referenced-by-count":0,"title":["Free-Moref: Instantly Multiplexing Context Perception Capabilities of Video-Mllms Within Single Inference"],"prefix":"10.1109","author":[{"given":"Kuo","family":"Wang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanlong","family":"Zheng","sequence":"additional","affiliation":[{"name":"OPPO AI Center, OPPO Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junlin","family":"Xie","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"OPPO AI Center, OPPO Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinguo","family":"Luo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Lu","sequence":"additional","affiliation":[{"name":"OPPO AI Center, OPPO Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Minigpt4-video: Advancing multimodal 11 ms for video understanding with interleaved visual-textual tokens","author":"Ataallah","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref6","article-title":"Fewer tokens and fewer videos: Extending video understanding abilities in large vision-language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref11","article-title":"Video-ccam: Enhancing video-language understanding with causal cross-attention masks for short and long videos","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","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":"ref13","article-title":"Prunevid: Visual token pruning for efficient video large language models","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"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":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref23","article-title":"Videogpt+: Integrating image and video encoders for enhanced video understanding","author":"Maaz","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01463"},{"key":"ref25","article-title":"Inf-mllm: Efficient streaming inference of multimodal large language models on a single gpu","author":"Ning","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref27","article-title":"Llava-prumerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02436"},{"key":"ref29","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","year":"2024","journal-title":"Internvl2: Better than the best-expanding performance boundaries of open-source multimodal models with the progressive scaling strategy"},{"key":"ref31","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","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":"ref33","article-title":"Retake: Reducing temporal and knowledge redundancy for long video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","first-page":"396","article-title":"Internvideo2: Scaling foundation models for multimodal video understanding","volume-title":"European Conference on Computer Vision","author":"Wang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755383"},{"key":"ref36","first-page":"453","article-title":"Longvlm: Efficient long video understanding via large language models","volume-title":"European Conference on Computer Vision","author":"Weng"},{"key":"ref37","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":"ref38","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Longvila: Scaling long-context visual language models for long videos","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","author":"Zhang","year":"2024","journal-title":"Lmmseval: Reality check on the evaluation of large multimodal models"},{"key":"ref42","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","author":"Zhang","year":"2024","journal-title":"Llava-next: A strong zero-shot video understanding model"},{"key":"ref44","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Mlvu: A comprehensive benchmark for multi-task long video understanding","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"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\/11445110.pdf?arnumber=11445110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:26Z","timestamp":1777613486000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02089","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}