{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:21:29Z","timestamp":1778052089749,"version":"3.51.4"},"reference-count":33,"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\/wacv61042.2026.00629","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6507-6516","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid State Representation for Video Procedure Planning"],"prefix":"10.1109","author":[{"given":"Woo Suk","family":"Choi","sequence":"first","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youwon","family":"Jang","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minsu","family":"Lee","sequence":"additional","affiliation":[{"name":"Sungshin Women’s University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byoung-Tak","family":"Zhang","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"ref3","article-title":"Abstract meaning representation for sembanking","author":"Banarescu","year":"2013","journal-title":"LAW@ACL"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01532"},{"key":"ref5","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013","journal-title":"Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.dlg4nlp-1.4"},{"key":"ref8","article-title":"Relational inductive bias for physical construction in humans and machines","author":"Hamrick","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511752902"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206795"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref14","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00945"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.122"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43156-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01780"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/S0266466603004109"},{"key":"ref21","article-title":"Schema: State changes matter for procedure planning in instructional videos","author":"Niu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01404"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref25","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","volume-title":"International Conference on Machine Learning","author":"Srinivas"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00893"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150855"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01425"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01973"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32992"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00295"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"}],"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\/11492608.pdf?arnumber=11492608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:39:26Z","timestamp":1778049566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00629","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}