{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:45Z","timestamp":1777889685679,"version":"3.51.4"},"reference-count":57,"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\/iccv51701.2025.02198","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23678-23688","source":"Crossref","is-referenced-by-count":0,"title":["DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding"],"prefix":"10.1109","author":[{"given":"Xiaoyi","family":"Bao","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenwei","family":"Xie","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingyu","family":"Weng","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref3","article-title":"Exploring visual prompts for adapting largescale models","author":"Bahng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27834"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref10","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref13","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref17","article-title":"Video-lavit: Unified video-language pre-training with decoupled visual-motional tokenization","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"ref21","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.161"},{"key":"ref23","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref29","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref32","article-title":"Ppllava: Varied video sequence understanding with prompt guidance","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00801"},{"key":"ref34","article-title":"Vista-llama: Reliable video narrator via equal distance to visual tokens","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00556"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref41","article-title":"Ufo: A unified approach to fine-grained visual perception via openended language interface","author":"Tang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref42","volume-title":"Qwen2.5: A party of foundation models","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3122865.3122867"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref49","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref51","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing visionlanguage understanding with advanced large language models"}],"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\/11445762.pdf?arnumber=11445762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:47Z","timestamp":1777612607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02198","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}