{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:53:46Z","timestamp":1761126826339,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Scholarship from Intergenepharm Pty Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3412330","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:37:16Z","timestamp":1718131036000},"page":"10755-10765","source":"Crossref","is-referenced-by-count":2,"title":["Point Clouds are Specialized Images: A Knowledge Transfer Approach for 3D Understanding"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-2462","authenticated-orcid":false,"given":"Jiachen","family":"Kang","sequence":"first","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0940-3338","authenticated-orcid":false,"given":"Wenjing","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8962-540X","authenticated-orcid":false,"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo, Ningbo, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8454","authenticated-orcid":false,"given":"Kin Man","family":"Lam","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9050741"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160658"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref9","first-page":"1","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2D image transformers help 3D representation learning?","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Dong","year":"2023"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref13","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bao","year":"2022"},{"key":"ref14","first-page":"1179","article-title":"ULIP: Learning a unified representation of language, images, and point clouds for 3D understanding","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Gao","year":"2023"},{"key":"ref15","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qi","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_38"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref20","first-page":"14388","article-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126882"},{"article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","year":"2021","author":"Liu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01335-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3284591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00727"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_36"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286708"},{"key":"ref29","first-page":"5105","article-title":"PointNet : Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Qi","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"issue":"1","key":"ref31","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"article-title":"ShapeNet: An information-rich 3D model repository","year":"2015","author":"Chang","key":"ref32"},{"key":"ref33","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2022"},{"key":"ref34","first-page":"492","article-title":"DISN: Deep implicit surface network for high-quality single-view 3D reconstruction","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Xu","year":"2019"},{"article-title":"Accelerating 3D deep learning with PyTorch3D","year":"2020","author":"Ravi","key":"ref35"},{"key":"ref36","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref37","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref39","first-page":"828","article-title":"PointCNN: Convolution on X-transformed points","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074240"},{"key":"ref41","first-page":"1","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2021"},{"key":"ref42","first-page":"23192","article-title":"PointNeXt: Revisiting PointNet with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Qian","year":"2022"},{"key":"ref43","first-page":"3086","article-title":"Self-supervised learning with multi-view rendering for 3D point cloud analysis","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Tran","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3282568"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref48","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"article-title":"P-Tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","year":"2021","author":"Liu","key":"ref49"},{"key":"ref50","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2023.102219"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103497"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10553392.pdf?arnumber=10553392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:26:07Z","timestamp":1732667167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10553392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3412330","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2024]]}}}