{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T15:20:42Z","timestamp":1788448842071,"version":"build-2803163510"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00811","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8668-8677","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Xia","sequence":"first","affiliation":[{"name":"University of Technology Sydney,Faculty of Engineering and IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yike","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney,Faculty of Engineering and IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjian","family":"Huang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Dept. of Comp. Sci. and Eng."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Dept. of Comp. Sci. and Eng."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney,Faculty of Engineering and IT"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep vit features as dense visual descriptors","volume-title":"ECCV Workshops","author":"Amir","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_15"},{"key":"ref3","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"NIPS","author":"Caron","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref6","first-page":"28104","article-title":"Unsupervised part discovery from contrastive reconstruction","author":"Choudhury","year":"2021","journal-title":"NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_21"},{"key":"ref8","article-title":"Vision transformers need registers","author":"Darcet","year":"2024","journal-title":"ICLR."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"ref10","first-page":"41714186","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"key":"ref11","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref12","first-page":"3576","article-title":"Unsupervised co-part segmentation through assembly","author":"Gao","year":"2021","journal-title":"ICML"},{"key":"ref13","first-page":"21271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NIPS"},{"key":"ref14","first-page":"40676","article-title":"Siamese masked autoencoders","volume-title":"NIPS","author":"Gupta","year":"2023"},{"key":"ref15","first-page":"128","article-title":"Partimagenet: A large, highquality dataset of parts","author":"He","year":"2022","journal-title":"ECCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00129"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00096"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00825"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"ref26","author":"Oquab","year":"2024","journal-title":"DINOv2: Learning robust visual features without supervision. TMLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_27"},{"key":"ref28","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI blog"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref32","first-page":"96509657","article-title":"Motionsupervised co-part segmentation","author":"Siarohin","year":"2021","journal-title":"ICPR"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.348"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00179"},{"key":"ref36","volume-title":"The Caltech-UCSD Birds-200\u20132011 Dataset","author":"Wah","year":"2011"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02147"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445582"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00400"},{"key":"ref42","first-page":"27127","article-title":"How mask matters: Towards theoretical understandings of masked autoencoders","author":"Zhang","year":"2022","journal-title":"NIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_12"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01410"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445189.pdf?arnumber=11445189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:23Z","timestamp":1777611323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00811","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}