{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:01:38Z","timestamp":1742954498505,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200496"},{"type":"electronic","value":"9783031200502"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20050-2_8","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"120-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatially Invariant Unsupervised 3D Object-Centric Learning and\u00a0Scene Decomposition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9032-8488","authenticated-orcid":false,"given":"Tianyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6485-3510","authenticated-orcid":false,"given":"Miaomiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0701-8783","authenticated-orcid":false,"given":"Kee Siong","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: ICML, pp. 40\u201349. PMLR (2018)","key":"8_CR1"},{"unstructured":"Alemi, A., Fischer, I., Dillon, J., Murphy, K.: Deep variational information bottleneck. In: ICLR (2017). https:\/\/arxiv.org\/abs\/1612.00410","key":"8_CR2"},{"unstructured":"Armeni, I., Sax, A., Zamir, A.R., Savarese, S.: Joint 2D\u20133D-Semantic Data for Indoor Scene Understanding. arXiv e-prints, February 2017","key":"8_CR3"},{"unstructured":"Bornschein, J., Mnih, A., Zoran, D., Rezende, D.J.: Variational memory addressing in generative models. In: NIPS (2017)","key":"8_CR4"},{"unstructured":"Burgess, C., et al.: Monet: unsupervised scene decomposition and representation. arXiv abs\/1901.11390 (2019). https:\/\/arxiv.org\/abs\/1901.11390","key":"8_CR5"},{"unstructured":"Burgess, C.P., et al.: Understanding disentangling in $$\\beta $$-VAE. arXiv abs\/1804.03599 (2018)","key":"8_CR6"},{"unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Technical report, arXiv:1512.03012 [cs.GR], Stanford University \u2013 Princeton University \u2013 Toyota Technological Institute at Chicago (2015)","key":"8_CR7"},{"unstructured":"Chang, B.M., Ullman, T., Torralba, A., Tenenbaum, B.J.: A compositional object-based approach to learning physical dynamics. In: ICLR (2017)","key":"8_CR8"},{"unstructured":"Chen, C., Deng, F., Ahn, S.: Roots: object-centric representation and rendering of 3D scenes (2021)","key":"8_CR9"},{"doi-asserted-by":"publisher","unstructured":"Crawford, E., Pineau, J.: Spatially invariant unsupervised object detection with convolutional neural networks. In: AAAI, vol. 33, pp. 3412\u20133420 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33013412","key":"8_CR10","DOI":"10.1609\/aaai.v33i01.33013412"},{"doi-asserted-by":"publisher","unstructured":"Crawford, E., Pineau, J.: Exploiting spatial invariance for scalable unsupervised object tracking. In: AAAI, vol. 34, pp. 3684\u20133692 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i04.5777","key":"8_CR11","DOI":"10.1609\/aaai.v34i04.5777"},{"doi-asserted-by":"publisher","unstructured":"Diuk, C., Cohen, A., Littman, M.L.: An object-oriented representation for efficient reinforcement learning. In: ICML, ICML 2008, pp. 240\u2013247. Association for Computing Machinery, New York (2008). https:\/\/doi.org\/10.1145\/1390156.1390187","key":"8_CR12","DOI":"10.1145\/1390156.1390187"},{"unstructured":"Engelcke, M., Kosiorek, A.R., Jones, O.P., Posner, I.: Genesis: generative scene inference and sampling with object-centric latent representations. In: ICLR (2020). https:\/\/openreview.net\/forum?id=BkxfaTVFwH","key":"8_CR13"},{"unstructured":"Eslami, S.M.A., et al.: Attend, infer, repeat: Fast scene understanding with generative models. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS 2016, pp. 3233\u20133241. Curran Associates Inc., Red Hook (2016)","key":"8_CR14"},{"doi-asserted-by":"crossref","unstructured":"Gadelha, M., Wang, R., Maji, S.: Multiresolution tree networks for 3D point cloud processing. In: ECCV, pp. 103\u2013118 (2018)","key":"8_CR15","DOI":"10.1007\/978-3-030-01234-2_7"},{"unstructured":"Greff, K., et al.: Multi-object representation learning with iterative variational inference. In: ICML (2019)","key":"8_CR16"},{"unstructured":"Greff, K., van Steenkiste, S., Schmidhuber, J.: Neural expectation maximization. In: NeurIPS, NIPS 2017, pp. 6694\u20136704. Curran Associates Inc., Red Hook (2017)","key":"8_CR17"},{"unstructured":"Henderson, P., Lampert, C.H.: Unsupervised object-centric video generation and decomposition in 3D. In: NeurIPS (2020)","key":"8_CR18"},{"unstructured":"Higgins, I., et al.: $$\\beta $$-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)","key":"8_CR19"},{"key":"8_CR20","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"L Hubert","year":"1985","unstructured":"Hubert, L., Arabie, P.: Comparing partitions. J. Classif. 2, 193\u2013218 (1985)","journal-title":"J. Classif."},{"unstructured":"Islam, M.A., Jia, S., Bruce, N.D.B.: How much position information do convolutional neural networks encode? In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=rJeB36NKvB","key":"8_CR21"},{"doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C.W., Jia, J.: Pointgroup: dual-set point grouping for 3D instance segmentation. In: CVPR (2020)","key":"8_CR22","DOI":"10.1109\/CVPR42600.2020.00492"},{"doi-asserted-by":"publisher","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning, pp. 1988\u20131997 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.215","key":"8_CR23","DOI":"10.1109\/CVPR.2017.215"},{"unstructured":"Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv abs\/1809.02627 (2020)","key":"8_CR24"},{"unstructured":"Kabra, R., et al.: Multi-object datasets (2019). https:\/\/github.com\/deepmind\/multi-object-datasets\/","key":"8_CR25"},{"doi-asserted-by":"publisher","unstructured":"Kahneman, D., Treisman, A., Gibbs, B.J.: The reviewing of object files: object-specific integration of information. Cogn. Psychol. 24(2), 175\u2013219 (1992). https:\/\/doi.org\/10.1016\/0010-0285(92)90007-O. https:\/\/www.sciencedirect.com\/science\/article\/pii\/001002859290007O","key":"8_CR26","DOI":"10.1016\/0010-0285(92)90007-O"},{"unstructured":"Kansky, K., et al.: Schema networks: zero-shot transfer with a generative causal model of intuitive physics. arXiv abs\/1706.04317 (2017)","key":"8_CR27"},{"unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)","key":"8_CR28"},{"unstructured":"Li, N., Eastwood, C., Fisher, R.: Learning object-centric representations of multi-object scenes from multiple views. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 5656\u20135666. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/3d9dabe52805a1ea21864b09f3397593-Paper.pdf","key":"8_CR29"},{"unstructured":"Lin, Z., et al.: Space: unsupervised object-oriented scene representation via spatial attention and decomposition. In: ICLR (2020). https:\/\/openreview.net\/forum?id=rkl03ySYDH","key":"8_CR30"},{"unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. In: NeurIPS (2020)","key":"8_CR31"},{"doi-asserted-by":"crossref","unstructured":"Luo, S., Hu, W.: Diffusion probabilistic models for 3D point cloud generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021","key":"8_CR32","DOI":"10.1109\/CVPR46437.2021.00286"},{"unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008). https:\/\/www.jmlr.org\/papers\/v9\/vandermaaten08a.html","key":"8_CR33"},{"doi-asserted-by":"crossref","unstructured":"Shi, W., Rajkumar, R.: Point-GNN: graph neural network for 3D object detection in a point cloud. In: CVPR, pp. 1708\u20131716 (2020)","key":"8_CR34","DOI":"10.1109\/CVPR42600.2020.00178"},{"unstructured":"Stelzner, K., Kersting, K., Kosiorek, A.R.: Decomposing 3D scenes into objects via unsupervised volume segmentation (2021)","key":"8_CR35"},{"unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. In: Proceedings of the 37th Annual Allerton Conference on Communication, Control and Computing, pp. 368\u2013377 (1999). https:\/\/arxiv.org\/abs\/physics\/0004057","key":"8_CR36"},{"doi-asserted-by":"publisher","unstructured":"Wu, W., Qi, Z., Li, F.: Pointconv: deep convolutional networks on 3D point clouds. In: CVPR, pp. 9613\u20139622 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00985","key":"8_CR37","DOI":"10.1109\/CVPR.2019.00985"},{"doi-asserted-by":"publisher","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: Pointflow: 3D point cloud generation with continuous normalizing flows, pp. 4540\u20134549 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00464","key":"8_CR38","DOI":"10.1109\/ICCV.2019.00464"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20050-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:22:28Z","timestamp":1666909348000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20050-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200496","9783031200502"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20050-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}