{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:50Z","timestamp":1778051510006,"version":"3.51.4"},"reference-count":68,"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\/wacv61042.2026.00274","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2797-2807","source":"Crossref","is-referenced-by-count":0,"title":["UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning"],"prefix":"10.1109","author":[{"given":"Huy","family":"Le","sequence":"first","affiliation":[{"name":"FPT Software AI Center,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nhat","family":"Chung","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tung","family":"Kieu","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,S-Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,AICV Lab,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02715"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref6","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i5.37337"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_13"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognitionat scale","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/321694.321699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3301975"},{"key":"ref15","article-title":"Slotvla: Towards modeling of object-relation representations in robotic manipulation","author":"Hanyu","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.685"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref20","article-title":"Improving object-centric learning with query optimization","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Jia"},{"key":"ref21","article-title":"Slot state space models","author":"Jiang","year":"2024","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01746"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01774"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28137"},{"key":"ref33","first-page":"11525","article-title":"Object-centric learning with slot attention","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Locatello"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612249"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02184"},{"key":"ref37","first-page":"29794","article-title":"Shaping embodied agent behavior with activity-context priors from egocentric video","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Nagarajan"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32665"},{"key":"ref39","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01529"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.278"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610695"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.365"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01343"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02639"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161478"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00732"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3442301"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548324"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref58","first-page":"726","article-title":"Do different tracking tasks require different appearance models?","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref60","first-page":"126","article-title":"Learning 3d dynamic scene representations for robot manipulation","volume-title":"Proceedings of the Conference on Robot Learning","author":"Xu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2336"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3053"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"ref64","article-title":"Object-centric learning for real-world videos by predicting temporal feature similarities","author":"Zadaianchuk","year":"2023","journal-title":"NeurIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3283879"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00310"},{"key":"ref67","article-title":"VIOLA: imitation learning for vision-based manipulation with object proposal priors","author":"Zhu","year":"2022","journal-title":"CoRR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351040"}],"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\/11492253.pdf?arnumber=11492253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:15:03Z","timestamp":1778048103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00274","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}