{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:40:42Z","timestamp":1779381642179,"version":"3.53.1"},"reference-count":62,"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\/iccv51701.2025.00904","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9693-9703","source":"Crossref","is-referenced-by-count":3,"title":["Tapnext: Tracking Any Point (Tap) as Next Token Prediction"],"prefix":"10.1109","author":[{"given":"Artem","family":"Zholus","sequence":"first","affiliation":[{"name":"Chandar Research Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carl","family":"Doersch","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Skanda","family":"Koppula","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viorica","family":"Patraucean","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu Owen","family":"He","sequence":"additional","affiliation":[{"name":"MakerMaker AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ignacio","family":"Rocco","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehdi S. M.","family":"Sajjadi","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarath","family":"Chandar","sequence":"additional","affiliation":[{"name":"Chandar Research Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Goroshin","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Track-On: Transformer-based online point tracking with memory","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Aydemir"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000011205.11775.fd"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02122"},{"key":"ref5","article-title":"Track2Act: Predicting point tracks from internet videos enables diverse zero-shot robot manipulation","author":"Bharadhwaj","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Gen2act: Human video generation in novel scenarios enables generalizable robot manipulation","volume-title":"CoRL Workshop on X- Embodiment","author":"Bharadhwaj","year":"2025"},{"key":"ref7","author":"Botev","year":"2024","journal-title":"RecurrentGemma: Moving past transformers for efficient open language models"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_18"},{"key":"ref10","author":"De","year":"2024","journal-title":"Griffin: Mixing gated linear recurrences with local attention for efficient language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0989"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0901-7_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref15","author":"Dosovitskiy","year":"2021","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref16","article-title":"Stop regressing: Training value functions via classification for scalable deep RL","volume-title":"Forty-first International Conference on Machine Learning","author":"Farebrother"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2792152"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref19","author":"Gu","year":"2024","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref20","author":"Gu","year":"2022","journal-title":"Efficiently modeling long sequences with structured state spaces"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref22","volume-title":"Multiple view geometry in computer vision","author":"Hartley","year":"2003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/5.265351"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref27","article-title":"CoTracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","article-title":"Tapvid-3d: A benchmark for tracking any point in 3d","author":"Koppula","year":"2024","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.363"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3205"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref36","article-title":"Unifying 3d representation and control of diverse robots with a single camera","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/1744-7917.13322"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1852"},{"key":"ref40","author":"P\u0103tr\u0103ucean","year":"2024","journal-title":"TRecViT: A Recurrent Video Transformer"},{"key":"ref41","article-title":"TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video","author":"Qu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Learning internal representations by error propagation, parallel distributed processing, explorations in the microstructure of cognition","volume":"1","author":"Rumelhart","year":"1986","journal-title":"Biometrika"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3372828"},{"key":"ref44","author":"T. H.","year":"2023","journal-title":"Simplified state space layers for sequence modeling"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610900"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"ref48","author":"Team","year":"2024","journal-title":"Gemma: Open models based on gemini research and technology"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"ref52","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Oord","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611409"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3592413"},{"key":"ref60","article-title":"General flow as foundation affordance for scalable robot learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"}],"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\/11445014.pdf?arnumber=11445014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:30Z","timestamp":1777529910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00904","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}