{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:43:11Z","timestamp":1766083391766,"version":"3.48.0"},"reference-count":115,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["62461160309"],"award-info":[{"award-number":["62461160309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403400"],"award-info":[{"award-number":["62403400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Oversea Excellent Young Scientist Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3566593","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:16:50Z","timestamp":1746191810000},"page":"7352-7368","source":"Crossref","is-referenced-by-count":0,"title":["General 3D Vision-Language Model With Fast Rendering and Pre-Training Vision-Language Alignment"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8387-3565","authenticated-orcid":false,"given":"Kangcheng","family":"Liu","sequence":"first","affiliation":[{"name":"Division of Engineering and Applied Science, California Institute of Technology (Caltech), Pasadena, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4702-036X","authenticated-orcid":false,"given":"Baoquan","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Lab of Genaral AI, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211006735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01690"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_3"},{"key":"ref5","first-page":"30798","article-title":"OGC: Unsupervised 3D object segmentation from rigid dynamics of point clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01886"},{"key":"ref7","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":"ref8","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref10","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01071"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00371"},{"article-title":"Segment everything everywhere all at once","year":"2023","author":"Zou","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01150"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3246102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_11"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3208735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01598"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"article-title":"Gated CRF loss for weakly supervised semantic image segmentation","year":"2019","author":"Obukhov","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00914"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3228174"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00506"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980567"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3098789"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00180"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00598"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"ref40","first-page":"21300","article-title":"Towards efficient 3D object detection with knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"article-title":"SoftGroup: Scalable 3D instance segmentation with octree pyramid grouping","year":"2022","author":"Vu","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00199"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00183"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00169"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00534"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01158"},{"key":"ref54","first-page":"1","article-title":"PSTNet: Point spatio-temporal convolution on point cloud sequences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983410"},{"key":"ref56","first-page":"965","article-title":"Point-voxel CNN for efficient 3D deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00425"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561496"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811959"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01296"},{"key":"ref62","first-page":"6735","article-title":"Spatial pruned sparse convolution for efficient 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00477"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00815"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00908"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3410324"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01874"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_17"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01710-9"},{"article-title":"SQN: Weakly-supervised semantic segmentation of large-scale 3D point clouds with 1000x fewer labels","year":"2021","author":"Hu","key":"ref79"},{"article-title":"Weakly supervised semantic segmentation in 3D graph-structured point clouds of wild scenes","year":"2020","author":"Wang","key":"ref80"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00444"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01740-3"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00177"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1142\/9789811286490_0003"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01372"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_28"},{"article-title":"Coarse3D: Class-prototypes for contrastive learning in weakly-supervised 3D point cloud segmentation","year":"2022","author":"Li","key":"ref87"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01688"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00426"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093545"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00107"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01438"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/BF00977785"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1982.1676031"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-4485(97)00082-1"},{"volume-title":"OpenGL Programming Guide: The Official Guide to Learning OpenGL","year":"2009","author":"Shreiner","key":"ref97"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/34.888718"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref102","first-page":"20520","article-title":"Differentiable top-k with optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00636"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_20"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25205"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0311-7"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_5"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref110"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01109"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3193614"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3131120"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/10982154.pdf?arnumber=10982154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:33:14Z","timestamp":1766082794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10982154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":115,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3566593","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}