{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:47Z","timestamp":1777865387127,"version":"3.51.4"},"reference-count":73,"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\/iccv51701.2025.02150","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23156-23166","source":"Crossref","is-referenced-by-count":0,"title":["One Trajectory, One Token: Grounded Video Tokenization Via Panoptic Sub-Object Trajectory"],"prefix":"10.1109","author":[{"given":"Chenhao","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammadreza","family":"Salehi","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqi","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishnu","family":"Iyengar","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norimasa","family":"Kobori","sequence":"additional","affiliation":[{"name":"Woven by Toyota, Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Kong","sequence":"additional","affiliation":[{"name":"Woven by Toyota, Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ranjay","family":"Krishna","sequence":"additional","affiliation":[{"name":"University of Washington"}],"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":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.721"},{"key":"ref6","article-title":"Subobject-level image tokenization","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0882"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref13","article-title":"An image is worth $16 x 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Sam2act: Integrating visual foundation model with a memory architecture for robotic manipulation","author":"Fang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref16","author":"Feichtenhofer","year":"2022","journal-title":"Masked autoencoders as spatiotemporal learners"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","volume":"33","author":"Jabri","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref24","author":"Jin","year":"2024","journal-title":"Video-lavit: Unified video-language pre-training with decoupled visual-motional tokenization"},{"key":"ref25","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref29","author":"Li","year":"2024","journal-title":"Lmms-eval: Accelerating the development of large multimoal models"},{"key":"ref30","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref35","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref37","article-title":"Ppllava: Varied video sequence understanding with prompt guidance","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref42","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","author":"Nagrani","year":"2021","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref44","author":"Pan","year":"2021","journal-title":"Ia-red2: Interpretability-aware redundancy reduction for vision transformers"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1163\/156856888X00122"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00785"},{"key":"ref48","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Tokenlearner: What can 8 learned tokens do for images and videos?","author":"Ryoo","year":"2021","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Longvu: Spatiotemporal adaptive compression for long video-language understanding","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02436"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1401_3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref57","first-page":"2024","article-title":"Global device growth and traffic profiles","author":"Systems","year":"2018","journal-title":"Technical report, Cisco"},{"key":"ref58","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1037\/a0029333"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref65","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01843"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref68","article-title":"Videoglue: Video general understanding evaluation of foundation models","author":"Yuan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","author":"Zhang","year":"2025","journal-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding"},{"key":"ref70","author":"Zhang","year":"2025","journal-title":"Llava-mini: Efficient image and video large multimodal models with one vision token"},{"key":"ref71","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Videoprism: A foundational visual encoder for video understanding","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","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\/11444787.pdf?arnumber=11444787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:14Z","timestamp":1777530194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02150","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}