{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:40:52Z","timestamp":1781836852753,"version":"3.54.5"},"reference-count":34,"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\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2112562"],"award-info":[{"award-number":["2112562"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF-23-2-0224"],"award-info":[{"award-number":["W911NF-23-2-0224"]}],"id":[{"id":"10.13039\/100000183","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\/iccv51701.2025.01934","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20802-20811","source":"Crossref","is-referenced-by-count":2,"title":["Keyframe-Oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-form Video Processing"],"prefix":"10.1109","author":[{"given":"Yudong","family":"Liu","sequence":"first","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwei","family":"Sun","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueqian","family":"Lin","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yin","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinsi","family":"Wang","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Token merging: Your ViT but faster","volume-title":"International Conference on Learning Representations","author":"Bolya"},{"key":"ref2","article-title":"Auroracap: Efficient, performant video detailed captioning and a new benchmark","author":"Chai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref7","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02438"},{"key":"ref10","article-title":"Egoschema: A diagnostic benchmark for very long-form video language understanding","author":"Malik","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref14","article-title":"Keyvideollm: Towards large-scale video keyframe selection","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref16","article-title":"SpeechPrune: Context-aware token pruning for speech information retrieval","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00538"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.eacl-long.164"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1852"},{"key":"ref22","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00403"},{"key":"ref26","article-title":"Llava-prumerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01289"},{"key":"ref28","article-title":"Videotree: Adaptive tree-based video representation for 11 m reasoning on long videos","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref34","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"}],"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\/11444792.pdf?arnumber=11444792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:49Z","timestamp":1777529989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01934","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}