{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:08Z","timestamp":1777890248727,"version":"3.51.4"},"reference-count":89,"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\/iccv51701.2025.00648","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6892-6903","source":"Crossref","is-referenced-by-count":0,"title":["O-MaMa: Learning Object Mask Matching Between Egocentric and Exocentric Views"],"prefix":"10.1109","author":[{"given":"Lorenzo","family":"Mur-Labadia","sequence":"first","affiliation":[{"name":"I3A - University of Zaragoza"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Santos-Villafranca","sequence":"additional","affiliation":[{"name":"I3A - University of Zaragoza"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesus","family":"Bermudez-Cameo","sequence":"additional","affiliation":[{"name":"I3A - University of Zaragoza"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Perez-Yus","sequence":"additional","affiliation":[{"name":"I3A - University of Zaragoza"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruben","family":"Martinez-Cantin","sequence":"additional","affiliation":[{"name":"I3A - University of Zaragoza"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose J.","family":"Guerrero","sequence":"additional","affiliation":[{"name":"I3A - University of Zaragoza"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00162"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref6","author":"Caelles","year":"2019","journal-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515428"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref11","first-page":"9011","article-title":"Cats: Cost aggregation transformers for visual correspondence","volume":"34","author":"Cho","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889421"},{"key":"ref14","first-page":"720","article-title":"Scaling egocentric vision: The Epic-Kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01766"},{"key":"ref17","author":"Dou","year":"2024","journal-title":"Unlocking exocentric video-language data for egocentric video representation learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"ref19","author":"Fu","year":"2024","journal-title":"Objectrelator: Enabling cross-view object relation understanding in ego-centric and exo-centric videos"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00808"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3115476"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(97)01067-X"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461143"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01794"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref44","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations, ICLR","author":"Loshchilov","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3191"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01445-z"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00483"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160606"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_10"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref54","author":"van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref55","author":"Oquab","year":"2023","journal-title":"DINOv2: Learning robust visual features without supervision"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_15"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00481"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref60","article-title":"Learning a non-linear knowledge transfer model for cross-view action recognition","author":"Rahmani","year":"2016","journal-title":"CVPR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.253"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21854"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01619"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.460"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.480"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3320231"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref72","first-page":"14254","article-title":"Disk: Learning local features with policy gradient","volume":"33","author":"Fua","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"5","key":"ref74","article-title":"Augmented reality (ar) applications: A survey on current trends, challenges, & future scope","volume":"8","author":"Vyas","year":"2017","journal-title":"International Journal of Advanced Research in Computer Science"},{"key":"ref75","author":"Wang","year":"2024","journal-title":"Visual object tracking across diverse data modalities: A review"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00273"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2336"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00102"},{"key":"ref82","first-page":"467","article-title":"Lift: Learned invariant feature transform","volume-title":"Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands,October 11\u201314, 2016, Proceedings, Part VI","volume":"14","author":"Moo Yi","year":"2016"},{"key":"ref83","article-title":"Joint attention learning for first and third person video co-analysis","author":"Yu","year":"2019","journal-title":"ACM MM"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref87","author":"Zhao","year":"2023","journal-title":"Fast segment anything"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3271000"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/11445651.pdf?arnumber=11445651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:28Z","timestamp":1777613548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00648","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}