{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:03:39Z","timestamp":1791911019533,"version":"4.3.4"},"reference-count":61,"publisher":"Tsinghua University Press","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.26599\/cvm.2025.9450437","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T13:55:54Z","timestamp":1749045354000},"page":"465-481","source":"Crossref","is-referenced-by-count":4,"title":["Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding"],"prefix":"10.26599","volume":"11","author":[{"given":"Yu-Qi","family":"Yang","sequence":"first","affiliation":[{"name":"Institute for Advanced Study, Tsinghua University,Beijing,China,100084"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Xiao","family":"Guo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16382"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.26599\/CVM.2025.9450383"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01849"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref8","article-title":"Point.Net++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3453485"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3194555"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00645"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01595"},{"key":"ref20","first-page":"33330","article-title":"Point transformer V2: Grouped vector attention and partition-based pooling","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Wu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref26","article-title":"Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling","author":"Wu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref28","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref31","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proceedings of the 36th Conference on Neural Information Processing Systems","author":"Zhang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00908"},{"key":"ref33","article-title":"3D feature prediction for masked-autoencoder-based point cloud pretraining","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_11"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3250241"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref48","article-title":"LargeKernel3D: Scaling up kernels in 3D CNNs","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00912"},{"key":"ref51","article-title":"Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01979"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref54","article-title":"PonderV2: Pave the way for 3D foundation model with A universal pre-training paradigm","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","first-page":"29975","article-title":"CAGroup3D: Class-aware grouping for 3D object detection on point clouds","volume-title":"Proceedings of the 36th Conference on Neural Information Processing Systems","author":"Wang","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"ref57","article-title":"V-DETR: DETR with vertex relative position encoding for 3D object detection","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681343"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11072531\/11024181.pdf?arnumber=11024181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:01Z","timestamp":1755910321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11024181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":61,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450437","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}