{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:20Z","timestamp":1777865300089,"version":"3.51.4"},"reference-count":51,"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\/iccv51701.2025.01942","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20889-20899","source":"Crossref","is-referenced-by-count":1,"title":["Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?"],"prefix":"10.1109","author":[{"given":"Tianyuan","family":"Qu","sequence":"first","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longxiang","family":"Tang","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohao","family":"Peng","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Senqiao","family":"Yang","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00232"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1684"},{"key":"ref7","article-title":"Longvila: Scaling long-context visual language models for long videos","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","article-title":"Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos","author":"Hu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000363"},{"key":"ref14","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"ref16","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref18","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00801"},{"key":"ref26","article-title":"Video-rag: Visually-aligned retrievalaugmented long video comprehension","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394293"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00642"},{"key":"ref34","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Lvbench: An extreme long video understanding benchmark","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103274"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35435"},{"key":"ref40","article-title":"Internvideo2. 5: Empowering video mllms with long and rich context modeling","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0907"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref43","article-title":"An improved baseline for reasoning segmentation with large language model","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01843"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.559"},{"key":"ref48","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Lyra: An efficient and speech-centric framework for omni-cognition","author":"Zhong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Mlvu: A comprehensive benchmark for multi-task long video understanding","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2900907"}],"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\/11445029.pdf?arnumber=11445029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:05Z","timestamp":1777529585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01942","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}