{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:35Z","timestamp":1792786895897,"version":"4.5.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Anhui Provincial Natural Science Foundation","award":["2508085MF142"],"award-info":[{"award-number":["2508085MF142"]}]},{"name":"New Generation Artificial Intelligence-National Science and Technology Major Project","award":["2025ZD0122603"],"award-info":[{"award-number":["2025ZD0122603"]}]},{"name":"ERC Advanced"},{"name":"Royal Academy of Engineering","award":["RF\\201819\\18\\163"],"award-info":[{"award-number":["RF\\201819\\18\\163"]}],"id":[{"id":"https:\/\/ror.org\/0526snb40","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3723656","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T19:05:27Z","timestamp":1786647927000},"page":"15198-15215","source":"Crossref","is-referenced-by-count":0,"title":["Text2Loc++: Generalizing 3D Point Cloud Localization From Natural Language"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6684-9814","authenticated-orcid":false,"given":"Yan","family":"Xia","sequence":"first","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Letian","family":"Shi","sequence":"additional","affiliation":[{"name":"Technical University of Munich","place":["Munich, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilin","family":"Di","sequence":"additional","affiliation":[{"name":"Technical University of Munich","place":["Munich, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joao F.","family":"Henriques","sequence":"additional","affiliation":[{"name":"University of Oxford","place":["Oxford, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3079-7984","authenticated-orcid":false,"given":"Daniel","family":"Cremers","sequence":"additional","affiliation":[{"name":"Technical University of Munich","place":["Munich, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02072"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3243470"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.01.027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00777"},{"key":"ref7","article-title":"Perception of vehicles and place recognition in urban environment based on MLS point clouds","author":"Xia","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0561"},{"key":"ref9","first-page":"887","article-title":"EgoNight: Towards egocentric vision understanding at night with a challenging benchmark","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2026"},{"issue":"140","key":"ref10","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"J. Mach. Learn. Res.","volume":"21","author":"Raffel","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00657"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0970"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25347"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246747"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00622"},{"issue":"22","key":"ref19","article-title":"Paris-CARLA-3D: A real and synthetic outdoor point cloud dataset for challenging tasks in 3D mapping","volume-title":"Remote Sens.","volume":"13","author":"Deschaud","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00109"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/rs12111875"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918767506"},{"key":"ref23","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref24","article-title":"DistilBERT, A distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref25","article-title":"LLAVADI: What matters for multimodal large language models distillation","author":"Xu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01417"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00470"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01119"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560932"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00028"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19934"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3170695"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178797"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21065-5_26"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3313635"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3434436"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00183"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.265"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11367-8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00117"},{"key":"ref46","article-title":"UniLoc: Towards universal place recognition using any single modality","author":"Xia","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00229"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2026.3676077"},{"issue":"5","key":"ref53","first-page":"5397","article-title":"Text to point cloud localization with multi-level negative contrastive learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"39","author":"Liu","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00777"},{"key":"ref55","article-title":"Spatialoc: Leveraging multi-level spatial enhanced descriptors for cross-modal localization","author":"Shang","year":"2026"},{"key":"ref56","article-title":"Riemannian and symplectic geometry for hierarchical text-driven place recognition","author":"Shang","year":"2026"},{"key":"ref57","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi","year":"2017"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref62","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref63","article-title":"GPT-4O system card","year":"2024"},{"key":"ref64","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref65","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref67","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi","year":"2013"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0786"},{"key":"ref69","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11654523.pdf?arnumber=11654523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:13:20Z","timestamp":1791486800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11654523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":69,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3723656","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}