{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T07:32:37Z","timestamp":1766820757233,"version":"build-2065373602"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62372016"],"award-info":[{"award-number":["62372016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535305","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T13:40:29Z","timestamp":1738676429000},"page":"3869-3879","source":"Crossref","is-referenced-by-count":3,"title":["Language-Assisted 3D Scene Understanding"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3926-4500","authenticated-orcid":false,"given":"Yanmin","family":"Wu","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Qiankun","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Renrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Multimedia Laboratory (MMLab), The Chinese University of HongKong, Shatin, N.T., Hong Kong, SAR, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Haijie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5486-3125","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"33330","article-title":"Point transformer V2: Grouped vector attention and partition-based pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wu","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450383"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3198318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304892"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01577"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref7","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3282568"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3314973"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110086"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3284591"},{"key":"ref13","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":"ref14","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bao","year":"2022"},{"key":"ref15","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref21","first-page":"35544","article-title":"Improving CLIP training with language rewrites","volume-title":"Proc. 37th Neural Inf. Process. Syst.","author":"Fan","year":"2024"},{"key":"ref22","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"ref27","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.","volume":"35","author":"Wang","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref29","first-page":"2639","article-title":"PointCLIP V2: Adapting CLIP for powerful 3D open-world learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28013"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3412330"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00790"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref36","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"},{"article-title":"Point-Bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","year":"2023","author":"Guo","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01296"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02088"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01644"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01873"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/icme57554.2024.10687626"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref56","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"article-title":"Shapenet: An information-rich 3D model repository","year":"2015","author":"Chang","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341580"},{"key":"ref62","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":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref64","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref65","first-page":"577","article-title":"Automatic choice of dimensionality for PCA","volume-title":"Proc. 31th Int. Conf. Neural Inf. Process. Syst.","author":"Minka","year":"2000"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-230710"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2023.102219"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10870118.pdf?arnumber=10870118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:18Z","timestamp":1752103218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10870118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535305","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}