{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:02:21Z","timestamp":1740132141692,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176060"],"award-info":[{"award-number":["62176060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22511105000"],"award-info":[{"award-number":["22511105000"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Lenovo Scientists Program"},{"name":"Program for Professor of Special Appointment"},{"name":"Shanghai Institutions of Higher Learning"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3349174","type":"journal-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T19:35:03Z","timestamp":1704310503000},"page":"3897-3909","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Object-Centric Learning From Multiple Unspecified Viewpoints"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9182-5563","authenticated-orcid":false,"given":"Jinyang","family":"Yuan","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2290-5612","authenticated-orcid":false,"given":"Tonglin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1849-0982","authenticated-orcid":false,"given":"Zhimeng","family":"Shen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9633-0033","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4897-9209","authenticated-orcid":false,"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2010.01127.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(88)90031-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S1355617797002889"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.171.3972.701"},{"volume-title":"Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information","year":"1982","author":"Marr","key":"ref6"},{"key":"ref7","first-page":"3225","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Eslami"},{"key":"ref8","first-page":"6694","article-title":"Neural expectation maximization","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Greff"},{"article-title":"MONet: Unsupervised scene decomposition and representation","year":"2019","author":"Burgess","key":"ref9"},{"key":"ref10","first-page":"2424","article-title":"Multi-object representation learning with iterative variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Greff"},{"key":"ref11","first-page":"11 515","article-title":"Object-centric learning with slot attention","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Locatello"},{"key":"ref12","first-page":"5656","article-title":"Learning object-centric representations of multi-object scenes from multiple views","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref13","first-page":"10 772","article-title":"Object-centric representation learning with generative spatial-temporal factorization","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Nanbo"},{"issue":"259","key":"ref14","first-page":"1","article-title":"ROOTS: Object-centric representation and rendering of 3D scenes","volume":"22","author":"Chen","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"20 146","article-title":"SIMONe: View-invariant, temporally-abstracted object representations via unsupervised video decomposition","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kabra"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20880"},{"key":"ref17","article-title":"Efficient inference in occlusion-aware generative models of images","author":"Huang","year":"2016","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref18","first-page":"7222","article-title":"Generative modeling of infinite occluded objects for compositional scene representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013412"},{"article-title":"SPACE: Unsupervised object-oriented scene representation via spatial attention and decomposition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019135"},{"key":"ref22","first-page":"2970","article-title":"Efficient iterative amortized inference for learning symmetric and disentangled multi-object representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Emami"},{"article-title":"Decomposing 3D scenes into objects via unsupervised volume segmentation","year":"2021","author":"Stelzner","key":"ref23"},{"article-title":"GENESIS: Generative scene inference and sampling with object-centric latent representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engelcke","key":"ref24"},{"key":"ref25","first-page":"12 572","article-title":"Generative neurosymbolic machines","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17290"},{"key":"ref27","article-title":"Relational neural expectation maximization: Unsupervised discovery of objects and their interactions","author":"van Steenkiste","year":"2018","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref28","first-page":"8615","article-title":"Sequential attend, infer, repeat: Generative modelling of moving objects","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kosiorek"},{"article-title":"R-SQAIR: Relational sequential attend, infer, repeat","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Stanic","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00141"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5777"},{"article-title":"SCALOR: Generative world models with scalable object representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang","key":"ref32"},{"key":"ref33","first-page":"1439","article-title":"Entity abstraction in visual model-based reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Veerapaneni"},{"key":"ref34","first-page":"2019","article-title":"PROVIDE: A probabilistic framework for unsupervised video decomposition","volume-title":"Proc. 37th Conf. Uncertainty Artif. Intell.","volume":"161","author":"Zablotskaia"},{"article-title":"Conditional object-centric learning from video","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","key":"ref35"},{"key":"ref36","first-page":"613","article-title":"Time-conditioned generative modeling of object-centric representations for video decomposition and prediction","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Gao"},{"issue":"183","key":"ref37","first-page":"1","article-title":"Benchmarking unsupervised object representations for video sequences","volume":"22","author":"Weis","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","first-page":"3403","article-title":"Iterative amortized inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Marino"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6170"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1214\/13-BA858"},{"article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","key":"ref42"},{"article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maddison","key":"ref43"},{"article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197332"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"article-title":"ShapeNet: An information-rich 3 D model repository","year":"2015","author":"Chang","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3286184"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10380320.pdf?arnumber=10380320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:47:16Z","timestamp":1725904036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10380320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":52,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3349174","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}