{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:24:02Z","timestamp":1781587442299,"version":"3.54.5"},"reference-count":95,"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":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20210324120603011"],"award-info":[{"award-number":["JCYJ20210324120603011"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271431"],"award-info":[{"award-number":["62271431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council of Hong Kong","award":["25207822"],"award-info":[{"award-number":["25207822"]}]},{"name":"Research Grants Council of Hong Kong","award":["15225522"],"award-info":[{"award-number":["15225522"]}]}],"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.2024.3410637","type":"journal-article","created":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:26:09Z","timestamp":1717694769000},"page":"8459-8473","source":"Crossref","is-referenced-by-count":6,"title":["Unsupervised 3D Object Segmentation of Point Clouds by Geometry Consistency"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7458-2491","authenticated-orcid":false,"given":"Ziyang","family":"Song","sequence":"first","affiliation":[{"name":"Shenzhen Research Institute, vLAR Group, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2419-4140","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute, vLAR Group, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"77","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00272"},{"key":"ref3","first-page":"6737","article-title":"Learning object bounding boxes for 3D instance segmentation on point clouds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3055766"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01288"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00410640"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/a0029333"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00709"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00097"},{"key":"ref11","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00410"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00564"},{"key":"ref15","first-page":"16938","article-title":"RigidFlow: Self-supervised scene flow learning on point clouds by local rigidity prior","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Wang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981210"},{"key":"ref17","first-page":"1","article-title":"OGC: Unsupervised 3d object segmentation from rigid dynamics of point clouds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00062"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00815"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00337"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00934"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_32"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00315"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00688"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01119"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00320"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00599"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01532"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275027"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00703"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561701"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00120"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_25"},{"key":"ref45","first-page":"1277","article-title":"Representation learning for object detection from unlabeled point cloud sequences","volume-title":"Proc. Conf. Robot Learn.","author":"Huang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00899"},{"key":"ref47","first-page":"3225","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Eslami"},{"key":"ref48","article-title":"MONet: Unsupervised scene decomposition and representation","author":"Burgess","year":"2019"},{"key":"ref49","first-page":"2424","article-title":"Multi-object representation learning with iterative variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gref"},{"key":"ref50","first-page":"1","article-title":"Object-centric learning with slot attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Locatello"},{"key":"ref51","first-page":"8615","article-title":"Sequential attend, infer, repeat: Generative modelling of moving objects","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kosiorek"},{"key":"ref52","first-page":"515","article-title":"Learning to decompose and disentangle representations for video prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hsieh"},{"key":"ref53","first-page":"92","article-title":"Unsupervised learning of object structure and dynamics from videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Minderer"},{"key":"ref54","first-page":"1","article-title":"SCALOR: Generative world models with scalable object representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01027"},{"key":"ref56","first-page":"9112","article-title":"Attention over learned object embeddings enables complex visual reasoning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref57","first-page":"4722","article-title":"Promising or elusive? unsupervised object segmentation from real-world single images","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.02.008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107861"},{"key":"ref60","first-page":"2226","article-title":"Layered image motion with explicit occlusions, temporal consistency, and depth ordering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247873"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00898"},{"key":"ref64","first-page":"13137","article-title":"The emergence of objectness : Learning zero-shot segmentation from videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref65","first-page":"1","article-title":"Conditional object-centric learning from video","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1107\/S0567739476001873"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00183"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767965"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref77","article-title":"3D motion segmentation of articulated rigid bodies based on RGB-D data","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Nunes"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.2307\/2282967"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"ref86","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3139542"},{"key":"ref93","article-title":"Openpcdet: An open-source toolbox for 3D object detection from point clouds","author":"Team","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00025"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01198"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10551495.pdf?arnumber=10551495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:25:31Z","timestamp":1732667131000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10551495\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":95,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3410637","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]]}}}