{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:51:17Z","timestamp":1779202277412,"version":"3.51.4"},"reference-count":61,"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\/iccv51701.2025.00595","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6304-6314","source":"Crossref","is-referenced-by-count":1,"title":["Manual-PA: Learning 3D Part Assembly from Instruction Diagrams"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Zhang","sequence":"first","affiliation":[{"name":"The Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anoop","family":"Cherian","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cristian","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"The Australian Institute for Machine Learning"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijian","family":"Deng","sequence":"additional","affiliation":[{"name":"The Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[{"name":"The Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"40","article-title":"Learning representations and generative models for 3d point clouds","volume-title":"ICML","author":"Achlioptas","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00430"},{"key":"ref4","first-page":"2229","article-title":"Domain generalization by solving jigsaw puzzles","author":"Fabio","year":"2019","journal-title":"CVPR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964930"},{"key":"ref7","article-title":"Zeropose: Cad-model-based zero-shot pose estimation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Score-pa: Score-based 3d part assembly","author":"Cheng","year":"2023","journal-title":"BMVC"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01970"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015775"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00962"},{"key":"ref14","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185551"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00092"},{"key":"ref17","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref20","article-title":"Megapose: 6d pose estimation of novel objects via render & compare","author":"Labb\u00e9","year":"2022","journal-title":"CoRL"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560986"},{"key":"ref22","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_40"},{"key":"ref24","article-title":"Rearrangement planning for general part assembly","volume-title":"7th Annual Conference on Robot Learning","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00316"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00072"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00227"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref32","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Dinov 2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref37","first-page":"652","article-title":"Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"Charles","year":"2017","journal-title":"CVPR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.640"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/2314570"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130821"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"issue":"6","key":"ref45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550454.3555525","article-title":"As-semble them all: Physics-based planning for generalizable assembly by disassembly","volume":"41","author":"Tian","year":"2022","journal-title":"ACM TOG"},{"key":"ref46","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801934"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_38"},{"key":"ref50","first-page":"28428","article-title":"Ikea-manual: Seeing shape assembly step by step","volume":"35","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00091"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00125"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00016"},{"key":"ref56","first-page":"6315","article-title":"Generative 3d part assembly via dynamic graph learning","volume":"33","author":"Zhan","year":"2020","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00245"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00786"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188098"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28556"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611259"}],"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\/11443346.pdf?arnumber=11443346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:13Z","timestamp":1777529413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00595","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}