{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T18:29:45Z","timestamp":1793384985297,"version":"4.5.0"},"reference-count":64,"publisher":"Tsinghua University Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.26599\/cvm.2025.9450383","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:36:22Z","timestamp":1740422182000},"page":"83-101","source":"Crossref","is-referenced-by-count":131,"title":["Swin3D: A Pretrained Transformer Backbone 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":"Internet Graphics Group, Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Yu","family":"Xiong","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China,518055"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Internet Graphics Group, Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Pan","sequence":"additional","affiliation":[{"name":"Internet Graphics Group, Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng-Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Tong","sequence":"additional","affiliation":[{"name":"Internet Graphics Group, Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baining","family":"Guo","sequence":"additional","affiliation":[{"name":"Internet Graphics Group, Microsoft Research Asia,Beijing,China,100080"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","volume-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref2","volume-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref3","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref15","volume-title":"Demystifying local vision transformer:Sparse connectivity, weight sharing, and dynamic weight","author":"Han","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20176"},{"key":"ref20","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proceeding of the 35th Conference on Neural Information Processing Systems","author":"Yang","year":"2021"},{"key":"ref21","volume-title":"SepViT: Separable vision transformer","author":"Li","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3341806\/mm1"},{"key":"ref23","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Chu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref25","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems","author":"Yuan","year":"2021"},{"key":"ref26","volume-title":"3D vision with transformers: A survey","author":"Lahoud","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref29","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":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01644"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16382"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref37","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Zhang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00908"},{"key":"ref41","first-page":"14388","article-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Wang","year":"2024"},{"key":"ref42","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2D image transformers help 3D representation learning?","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Dong","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28013"},{"key":"ref45","volume-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01426-8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"ref50","first-page":"29975","article-title":"CAGroup3D: Class-aware grouping for 3D object detection on point clouds","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Wang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01296"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref54","volume-title":"Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities","author":"Wang","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref57","volume-title":"Arkitscenes: A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data","author":"Baruch","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00327"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_18"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00459"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3453485"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.04.013"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10903665\/10901941.pdf?arnumber=10901941","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:34:44Z","timestamp":1741714484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10901941\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":64,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450383","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}