{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:10Z","timestamp":1777888990629,"version":"3.51.4"},"reference-count":71,"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\/iccv51701.2025.00617","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6541-6551","source":"Crossref","is-referenced-by-count":0,"title":["Mosic: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning"],"prefix":"10.1109","author":[{"given":"Mohammadreza","family":"Salehi","sequence":"first","affiliation":[{"name":"VIS Lab, UvA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shashanka","family":"Venkataramanan","sequence":"additional","affiliation":[{"name":"Valeo.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioana","family":"Simion","sequence":"additional","affiliation":[{"name":"VIS Lab, UvA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[{"name":"VIS Lab, UvA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[{"name":"VIS Lab, UvA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki M","family":"Asano","sequence":"additional","affiliation":[{"name":"Fundamental AI Lab, UTN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.13"},{"key":"ref2","article-title":"Dense unsupervised learning for video segmentation","author":"Araslanov","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Asano","year":"2020","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref5","article-title":"Towards in-context scene understanding","author":"Balazevic","year":"2023","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Object discovery from motionguided tokens","author":"Bao","year":"2023","journal-title":"ICCV"},{"key":"ref7","article-title":"Revisiting feature prediction for learning visual representations from video","author":"Bardes","year":"2024","journal-title":"TMLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref9","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","article-title":"Scaling 4d representations","author":"Carreira","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02716"},{"key":"ref13","article-title":"Learning to estimate pose by watching videos","author":"Chakraborty","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref15","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"Cuturi","year":"2013","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Vision transformers need registers","author":"Darcet","year":"2024","journal-title":"ICLR"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref18","volume-title":"The PASCAL Visual Object Classes Challenge2012 (VOC2012) Results","author":"Everingham","year":"2012"},{"key":"ref19","article-title":"Watching the world go by: Representation learning from unlabeled videos","author":"Gordon","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Accelerating largescale inference with anisotropic vector quantization","author":"Guo","year":"2020","journal-title":"ICML"},{"key":"ref22","article-title":"Stego: Unsupervised semantic segmentation by distilling feature correspondences","author":"Hamilton","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"ref25","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref29","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4324\/9781315009292"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02124"},{"key":"ref35","article-title":"Smooseg: smoothness prior for unsupervised semantic segmentation","author":"Lan","year":"2023","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Cribo: Self-supervised learning via cross-image object-level bootstrapping","author":"Lebailly","year":"2024","journal-title":"ICLR"},{"key":"ref37","article-title":"Joint-task self-supervised learning for temporal correspondence","author":"Li","year":"2019","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00818"},{"key":"ref41","article-title":"You don\u2019t need domainspecific data augmentations when scaling self-supervised learning","author":"Moutakanni","year":"2025","journal-title":"NeurIPS"},{"key":"ref42","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref43","volume-title":"Hummingbird evaluation for vision encoders","author":"Pariza","year":"2024"},{"key":"ref44","article-title":"Near, far:Patch-ordering enhances vision foundation models\u2019 scene understanding","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Pariza","year":"2025"},{"key":"ref45","article-title":"Self-supervised video pretraining yields humanaligned visual representations","author":"Parthasarathy","year":"2023","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.638"},{"key":"ref48","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01516"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_17"},{"key":"ref52","article-title":"Bridging the gap to real-world object-centric learning","author":"Seitzer","year":"2023","journal-title":"ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00310"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00676"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref56","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01382"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref60","article-title":"Moving off-thegrid: Scene-grounded video representations","author":"van Steenkiste","year":"2025","journal-title":"NeurIPS"},{"key":"ref61","article-title":"Is imagenet worth 1 video? learning strong image encoders from 1 long unlabelled video","author":"Venkataramanan","year":"2024","journal-title":"ICLR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01003"},{"key":"ref65","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00817"},{"key":"ref67","article-title":"Unsupervised semantic segmentation with self-supervised object-centric representations","author":"Zadaianchuk","year":"2023","journal-title":"ICLR"},{"key":"ref68","article-title":"Object-centric learning for real-world videos by predicting temporal feature similarities","author":"Zadaianchuk","year":"2023","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref70","article-title":"ibot: Image bert pre-training with online tokenizer","author":"Zhou","year":"2022","journal-title":"ICLR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01410"}],"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\/11446189.pdf?arnumber=11446189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:29Z","timestamp":1777611869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00617","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}