{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:46:52Z","timestamp":1777654012708,"version":"3.51.4"},"reference-count":74,"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\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202006130004"],"award-info":[{"award-number":["202006130004"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"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.2024.3445582","type":"journal-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:28:45Z","timestamp":1724074125000},"page":"10597-10613","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Part Discovery via Dual Representation Alignment"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9628-9563","authenticated-orcid":false,"given":"Jiahao","family":"Xia","sequence":"first","affiliation":[{"name":"Faculty of Engineering and IT, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2408-8302","authenticated-orcid":false,"given":"Wenjian","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9581-8849","authenticated-orcid":false,"given":"Min","family":"Xu","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and IT, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9317-0268","authenticated-orcid":false,"given":"Jianguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0021-3634","authenticated-orcid":false,"given":"Haimin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and IT, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1517-3290","authenticated-orcid":false,"given":"Ziyu","family":"Sheng","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and IT, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_22"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_40"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref7","article-title":"Vision transformers need registers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Darcet"},{"key":"ref8","article-title":"Localizing objects with self-supervised transformers and no labels","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Sim\u00e9oni"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305122"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00442"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00310"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00073"},{"key":"ref14","article-title":"Deep ViT features as dense visual descriptors","volume-title":"Proc. Eur. Conf. Comput. Vis. Workshops","author":"Amir"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"ref18","article-title":"The Caltech-UCSD Birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref21","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00289"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00265"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref26","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Caron"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01410"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref32","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref34","first-page":"40676","article-title":"Siamese masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01183-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.186"},{"key":"ref39","first-page":"7256","article-title":"Emergence of object segmentation in perturbed generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bielski"},{"key":"ref40","first-page":"29","article-title":"Unsupervised object segmentation by redrawing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00097"},{"key":"ref42","first-page":"10596","article-title":"Object segmentation without labels with large-scale generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Voynov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00179"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_12"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.348"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01121"},{"key":"ref49","first-page":"4020","article-title":"Unsupervised learning of object landmarks through conditional image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jakab"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00646"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"ref52","first-page":"10724","article-title":"Unsupervised learning of object keypoints for perception and control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kulkarni"},{"key":"ref53","first-page":"3814","article-title":"Unsupervised keypoint learning for guiding class-conditional video prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref54","first-page":"92","article-title":"Unsupervised learning of object structure and dynamics from videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Minderer"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref56","first-page":"29538","article-title":"Tusk: Task-agnostic unsupervised keypoints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00825"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00096"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_21"},{"key":"ref60","first-page":"28104","article-title":"Unsupervised part discovery from contrastive reconstruction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choudhury"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00129"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00400"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412520"},{"key":"ref64","first-page":"3576","article-title":"Unsupervised co-part segmentation through assembly","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref65","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref69","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"ref73","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kaiming"},{"key":"ref74","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10638824.pdf?arnumber=10638824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:43:33Z","timestamp":1755546213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":74,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3445582","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]]}}}