{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T22:36:40Z","timestamp":1784673400901,"version":"3.55.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00342","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3504-3513","source":"Crossref","is-referenced-by-count":1,"title":["SPOC: Spatially-Progressing Object State Change Segmentation in Video"],"prefix":"10.1109","author":[{"given":"Priyanka","family":"Mandikal","sequence":"first","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tushar","family":"Nagarajan","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Stoken","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihui","family":"Xue","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.234"},{"key":"ref2","article-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation","author":"Caelles","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref7","article-title":"Segment and track anything","author":"Cheng","year":"2023"},{"key":"ref8","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"European Conference on Computer Vision (ECCV)","author":"Damen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01766"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref13","volume-title":"Toronto annotation suite","author":"Kar","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.318"},{"key":"ref20","article-title":"VIP: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref21","article-title":"Liv: Language-image representations and rewards for robotic control","author":"Ma","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.129"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"ref27","year":"2023","journal-title":"Gpt-4. Technical report"},{"key":"ref28","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00369"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref35","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01375"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01357"},{"key":"ref38","article-title":"Multi-task learning of object state changes from uncurated videos","volume-title":"TPAMI","author":"Sou\u010dek"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00627"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02187"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00289"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01750"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2632"},{"key":"ref45","article-title":"Associating objects with transformers for video object segmentation","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01869"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01869"},{"key":"ref48","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492293.pdf?arnumber=11492293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:37Z","timestamp":1778048197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00342","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}