{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:54:01Z","timestamp":1791485641572,"version":"4.3.4"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grant Council - Early Career Scheme","award":["27209621"],"award-info":[{"award-number":["27209621"]}]},{"name":"General Research Fund Scheme","award":["17202422"],"award-info":[{"award-number":["17202422"]}]},{"name":"Theme-based Research","award":["T45-702\/22-R"],"award-info":[{"award-number":["T45-702\/22-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3401409","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T13:36:51Z","timestamp":1715780211000},"page":"8410-8423","source":"Crossref","is-referenced-by-count":2,"title":["Object-Centric Representation Learning for Video Scene Understanding"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3223-9035","authenticated-orcid":false,"given":"Yi","family":"Zhou","sequence":"first","affiliation":[{"name":"Samsung R&D Institute China-Beijing (SRC-B), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9912-1157","authenticated-orcid":false,"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute China-Beijing (SRC-B), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7304-3330","authenticated-orcid":false,"given":"Seung-In","family":"Park","sequence":"additional","affiliation":[{"name":"Samsung Advanced Institute of Technology, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4065-7512","authenticated-orcid":false,"given":"ByungIn","family":"Yoo","sequence":"additional","affiliation":[{"name":"Samsung Advanced Institute of Technology, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-1626","authenticated-orcid":false,"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00399"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01354"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_35"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"ref14","article-title":"TransTrack: Multiple-object tracking with transformer","author":"Sun","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00310"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01073"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00273"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00168"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref28","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref30","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref33","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume":"34","author":"Hwang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref34","first-page":"23109","article-title":"Vita: Video instance segmentation via object token association","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01797"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54193-8_16"},{"key":"ref39","article-title":"GENESIS: Generative scene inference and sampling with object-centric latent representations","author":"Engelcke","year":"2019"},{"key":"ref40","article-title":"Object-centric learning with slot attention","author":"Locatello","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636592"},{"key":"ref42","article-title":"Recurrent attention models with object-centric capsule representation for multi-object recognition","author":"Adeli","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref46","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. 27th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Eigen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.243"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6991"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref52","article-title":"Mmdetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref55","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_40"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7244"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10531009.pdf?arnumber=10531009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T19:18:19Z","timestamp":1732648699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10531009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":62,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3401409","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}