{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:47:06Z","timestamp":1778082426198,"version":"3.51.4"},"reference-count":77,"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\/iccv51701.2025.00616","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6530-6540","source":"Crossref","is-referenced-by-count":1,"title":["ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives"],"prefix":"10.1109","author":[{"given":"Yuqian","family":"Fu","sequence":"first","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runze","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Ren","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guolei","family":"Sun","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Gong","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danda Pani","family":"Paudel","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanjing","family":"Huang","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3536218"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref6","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"European conference on computer Vision","author":"Damen"},{"key":"ref7","volume-title":"Guide to the carnegie mellon university multimodal activity (cmu-mmac) database","author":"De la Torre","year":"2009"},{"key":"ref8","article-title":"Openvocabulary universal image segmentation with maskclip","author":"Ding","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-020-00195-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00758"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02084"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127599"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_46"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0242"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12256"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.003"},{"key":"ref34","article-title":"Crossviewdiff: A cross-view diffusion model for satellite-to-street view synthesis","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref36","volume-title":"Textbooks are all you need ii: phi-1.5 technical report","author":"Li","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0550"},{"key":"ref39","article-title":"Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification","author":"Lin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","article-title":"Exocentric-to-egocentric video generation","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Liu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","article-title":"Intention-driven ego-to-exo video generation","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_23"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00773"},{"key":"ref47","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01103"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0177-5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref52","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.07.008"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.40"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref57","article-title":"Learning co-segmentation by segment swapping for retrieval and discovery","author":"Shen","year":"2021","journal-title":"arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01650"},{"key":"ref59","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Xtrack: Multimodal training boosts rgb-x video object trackers","author":"Tan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00252"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.216"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2505083"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_28"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01278"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3390\/rs16020278"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref76","article-title":"Camsam2: Segment anything accurately in camouflaged videos","author":"Zhou","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref77","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11443357.pdf?arnumber=11443357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:20Z","timestamp":1777529420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00616","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}