{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:33:49Z","timestamp":1778258029567,"version":"3.51.4"},"reference-count":49,"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 Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFF0507603"],"award-info":[{"award-number":["2024YFF0507603"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.02047","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22046-22055","source":"Crossref","is-referenced-by-count":1,"title":["Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Zhang","sequence":"first","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuokai","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaorun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenghui","family":"Ding","sequence":"additional","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianjun","family":"Yang","sequence":"additional","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yining","family":"Sun","sequence":"additional","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref2","article-title":"Token merging: Your ViT but faster","volume-title":"International Conference on Learning Representations","author":"Bolya"},{"key":"ref3","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Chen"},{"key":"ref4","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":"ref5","article-title":"Hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","author":"Cheng","year":"2024","journal-title":"VideoLLaMA: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref8","article-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"ref12","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01099"},{"key":"ref14","author":"Li","year":"2022","journal-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref23","author":"Ma","year":"2023","journal-title":"Vista-LLaMA: Reliable Video Narrator via Equal Distance to Visual Tokens"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref27","article-title":"Foundation models for video understanding: A survey","author":"Madan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref29","article-title":"Mm1: Methods, analysis & insights from multimodal llm pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00914"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3566695"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref35","author":"Wu","year":"2024","journal-title":"Freeva: Offline mllm as training-free video assistant"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref38","author":"Xu","year":"2024","journal-title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning"},{"key":"ref39","author":"Xu","year":"2024","journal-title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref44","article-title":"Ferret-v2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","author":"Zhang","year":"2024","journal-title":"Llava-next: A strong zero-shot video understanding model"},{"key":"ref46","author":"Zhang","year":"2024","journal-title":"Llava-next: A strong zero-shot video understanding model"},{"key":"ref47","article-title":"Rankclip: Ranking-consistent language-image pretraining","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645412"},{"key":"ref49","article-title":"A survey on generative ai and llm for video generation, understanding, and streaming","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\/11444745.pdf?arnumber=11444745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:08Z","timestamp":1777612028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02047","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}