{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:08:54Z","timestamp":1777889334971,"version":"3.51.4"},"reference-count":67,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476099,62076101"],"award-info":[{"award-number":["62476099,62076101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024B1515020082,2023A1515010007"],"award-info":[{"award-number":["2024B1515020082,2023A1515010007"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02427","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26156-26166","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning"],"prefix":"10.1109","author":[{"given":"Yiyang","family":"Chen","sequence":"first","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanshan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commerce Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lunhao","family":"Duan","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commerce Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changxing","family":"Ding","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"ref7","author":"Chen","year":"2023","journal-title":"Videocrafter1: Open diffusion models for high-quality video generation"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_20"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2571"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2d image transformers help 3d representation learning?","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Dong","year":"2023"},{"key":"ref14","first-page":"3809","article-title":"Revisiting point cloud shape classification with a simple and effective baseline","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Goyal","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref16","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01564"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref23","article-title":"Pointcnn: Convolution on x-transformed points","volume-title":"Advances in Neural Information Processing Systems","author":"Li","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00951"},{"key":"ref27","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Rethinking network design and local geometry in point cloud: A simple residual mlp framework","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00290"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref33","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi","year":"2017"},{"key":"ref34","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","volume-title":"International Conference on Machine Learning (ICML)","author":"Qi","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1685"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref38","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","first-page":"7212","article-title":"Self-supervised few-shot learning on point clouds","volume":"33","author":"Sharma","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3402232"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00341"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"issue":"11","key":"ref46","article-title":"Visualizing data using t-sne","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28380"},{"key":"ref49","first-page":"14388","article-title":"P2p: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume-title":"Advances in Neural Information Processing Systems","author":"Wang","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00519"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00907"},{"key":"ref56","article-title":"Disdiff: Unsupervised disentanglement of diffusion probabilistic models","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Diffusion model with cross attention as an inductive bias for disentanglement","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref60","article-title":"Exploring diffusion timesteps for unsupervised representation learning","author":"Yue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28522"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1962"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1607"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02164"}],"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\/11446252.pdf?arnumber=11446252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:48Z","timestamp":1777612188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02427","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}