{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:04:41Z","timestamp":1768453481696,"version":"3.49.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198175","type":"print"},{"value":"9783031198182","type":"electronic"}],"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\/978-3-031-19818-2_41","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"719-735","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Unsupervised Segmentation in\u00a0Real-World Images via\u00a0Spelke Object Inference"],"prefix":"10.1007","author":[{"given":"Honglin","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Venkatesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoni","family":"Friedman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel L. K.","family":"Yamins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel M.","family":"Bear","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"41_CR1","unstructured":"Arora, T., Li, L.E., Cai, M.B.: Learning to perceive objects by prediction. In: SVRHM 2021 Workshop@ NeurIPS (2021)"},{"key":"41_CR2","unstructured":"Bear, D., et al.: Learning physical graph representations from visual scenes. In: Advances in Neural Information Processing Systems 33, pp. 6027\u20136039 (2020)"},{"key":"41_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/978-3-642-33783-3_44","volume-title":"Computer Vision \u2013 ECCV 2012","author":"DJ Butler","year":"2012","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611\u2013625. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_44"},{"key":"41_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al.: Panoptic-DeepLab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12475\u201312485 (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"41_CR7","unstructured":"Dorfman, N., Harari, D., Ullman, S.: Learning to perceive coherent objects. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 35 (2013)"},{"key":"41_CR8","unstructured":"Du, Y., Smith, K., Ulman, T., Tenenbaum, J., Wu, J.: Unsupervised discovery of 3D physical objects from video. arXiv preprint arXiv:2007.12348 (2020)"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Ebert, F., et al.: Bridge data: boosting generalization of robotic skills with cross-domain datasets. arXiv preprint arXiv:2109.13396 (2021)","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"41_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-01249-6_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"P Follmann","year":"2018","unstructured":"Follmann, P., B\u00f6ttger, T., H\u00e4rtinger, P., K\u00f6nig, R., Ulrich, M.: MVTec D2S: densely segmented supermarket dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 581\u2013597. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_35"},{"issue":"5814","key":"41_CR11","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","volume":"315","author":"BJ Frey","year":"2007","unstructured":"Frey, B.J., Dueck, D.: Clustering by passing messages between data points. Science 315(5814), 972\u2013976 (2007)","journal-title":"Science"},{"key":"41_CR12","unstructured":"Gan, C., et al.: ThreeDWorld: a platform for interactive multi-modal physical simulation. arXiv preprint arXiv:2007.04954 (2020)"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Gao, N., et al.: SSAP: single-shot instance segmentation with affinity pyramid. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 642\u2013651 (2019)","DOI":"10.1109\/ICCV.2019.00073"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"41_CR15","unstructured":"Greff, K., et al.: Multi-object representation learning with iterative variational inference. In: International Conference on Machine Learning, pp. 2424\u20132433. PMLR (2019)"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Gregory, S.: Finding overlapping communities in networks by label propagation. New J. Phys. 12(10), 103018 (2010)","DOI":"10.1088\/1367-2630\/12\/10\/103018"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"41_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"41_CR19","unstructured":"Hinton, G.: How to represent part-whole hierarchies in a neural network. arXiv preprint arXiv:2102.12627 (2021)"},{"key":"41_CR20","unstructured":"Kabra, R., et al.: SIMONe: view-invariant, temporally-abstracted object representations via unsupervised video decomposition. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"41_CR21","unstructured":"Kipf, T., et al.: Conditional object-centric learning from video. arXiv preprint arXiv:2111.12594 (2021)"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"41_CR23","unstructured":"Liu, W., Rabinovich, A., Berg, A.C.: ParseNet: looking wider to see better. arXiv preprint arXiv:1506.04579 (2015)"},{"key":"41_CR24","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. In: Advances in Neural Information Processing Systems 33, pp. 11525\u201311538 (2020)"},{"key":"41_CR25","unstructured":"Luo, L., Xiong, Y., Liu, Y., Sun, X.: Adaptive gradient methods with dynamic bound of learning rate. arXiv preprint arXiv:1902.09843 (2019)"},{"issue":"3","key":"41_CR26","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1016\/j.patcog.2012.09.015","volume":"46","author":"B Peng","year":"2013","unstructured":"Peng, B., Zhang, L., Zhang, D.: A survey of graph theoretical approaches to image segmentation. Pattern Recogn. 46(3), 1020\u20131038 (2013)","journal-title":"Pattern Recogn."},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Perazzi, F., et al.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"issue":"1","key":"41_CR28","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1146\/annurev.neuro.29.051605.112939","volume":"29","author":"PR Roelfsema","year":"2006","unstructured":"Roelfsema, P.R., et al.: Cortical algorithms for perceptual grouping. Ann. Rev. Neurosci. 29(1), 203\u2013227 (2006)","journal-title":"Ann. Rev. Neurosci."},{"issue":"4","key":"41_CR29","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TPAMI.2008.109","volume":"31","author":"MG Ross","year":"2008","unstructured":"Ross, M.G., Kaelbling, L.P.: Segmentation according to natural examples: learning static segmentation from motion segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 31(4), 661\u2013676 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR30","unstructured":"Sabour, S., Tagliasacchi, A., Yazdani, S., Hinton, G., Fleet, D.J.: Unsupervised part representation by flow capsules. In: International Conference on Machine Learning, pp. 9213\u20139223. PMLR (2021)"},{"issue":"8","key":"41_CR31","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888\u2013905 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR32","unstructured":"Sim\u00e9oni, O., et al.: Localizing objects with self-supervised transformers and no labels. arXiv preprint arXiv:2109.14279 (2021)"},{"issue":"1","key":"41_CR33","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1207\/s15516709cog1401_3","volume":"14","author":"ES Spelke","year":"1990","unstructured":"Spelke, E.S.: Principles of object perception. Cogn. Sci. 14(1), 29\u201356 (1990)","journal-title":"Cogn. Sci."},{"key":"41_CR34","unstructured":"Tangemann, M., et al.: Unsupervised object learning via common fate. arXiv preprint arXiv:2110.06562 (2021)"},{"key":"41_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"issue":"12","key":"41_CR36","doi-asserted-by":"publisher","first-page":"5345","DOI":"10.4249\/scholarpedia.5345","volume":"3","author":"D Todorovic","year":"2008","unstructured":"Todorovic, D.: Gestalt principles. Scholarpedia 3(12), 5345 (2008)","journal-title":"Scholarpedia"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Tsao, T., Tsao, D.Y.: A topological solution to object segmentation and tracking. arXiv preprint arXiv:2107.02036 (2021)","DOI":"10.1073\/pnas.2204248119"},{"issue":"44","key":"41_CR38","doi-asserted-by":"publisher","first-page":"18215","DOI":"10.1073\/pnas.1207690109","volume":"109","author":"S Ullman","year":"2012","unstructured":"Ullman, S., Harari, D., Dorfman, N.: From simple innate biases to complex visual concepts. Proc. Natl. Acad. Sci. 109(44), 18215\u201318220 (2012)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, X., Hu, S., Yuan, Y., Crowley, J., Vaufreydaz, D.: Self-supervised transformers for unsupervised object discovery using normalized cut. arXiv preprint arXiv:2202.11539 (2022)","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Yang, C., Lamdouar, H., Lu, E., Zisserman, A., Xie, W.: Self-supervised video object segmentation by motion grouping. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7177\u20137188 (2021)","DOI":"10.1109\/ICCV48922.2021.00709"},{"issue":"17","key":"41_CR41","doi-asserted-by":"publisher","first-page":"6594","DOI":"10.1523\/JNEUROSCI.20-17-06594.2000","volume":"20","author":"H Zhou","year":"2000","unstructured":"Zhou, H., Friedman, H.S., Von Der Heydt, R.: Coding of border ownership in monkey visual cortex. J. Neurosci. 20(17), 6594\u20136611 (2000)","journal-title":"J. Neurosci."},{"key":"41_CR42","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"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\/978-3-031-19818-2_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T14:40:23Z","timestamp":1710340823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19818-2_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198175","9783031198182"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19818-2_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 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)"}}]}}