{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:56:36Z","timestamp":1784300196966,"version":"3.55.0"},"reference-count":70,"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\/100015811","name":"Science and Technology Project of Hainan Provincial Department of Transportation","doi-asserted-by":"publisher","award":["HNJTT-KXC-2024-3-22-02"],"award-info":[{"award-number":["HNJTT-KXC-2024-3-22-02"]}],"id":[{"id":"10.13039\/100015811","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272018"],"award-info":[{"award-number":["62272018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3546853","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:50:56Z","timestamp":1741715456000},"page":"1737-1752","source":"Crossref","is-referenced-by-count":5,"title":["LangLoc: Language-Driven Localization via Formatted Spatial Description Generation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2344-1025","authenticated-orcid":false,"given":"Weimin","family":"Shi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8341-6399","authenticated-orcid":false,"given":"Changhao","family":"Chen","sequence":"additional","affiliation":[{"name":"Thrust of Intelligent Transportation and the Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1716-4381","authenticated-orcid":false,"given":"Kaige","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-4998","authenticated-orcid":false,"given":"Yuan","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5825-7517","authenticated-orcid":false,"given":"Zhong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"14975","article-title":"VIMA: General robot manipulation with multimodal prompts","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jiang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818931"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3115454"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228521"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28906"},{"key":"ref8","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv:2307.05973"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00277"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00288"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3310929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197981"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3383914"},{"key":"ref17","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Brown"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2299799"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08992-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01682"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_33"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01225"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02220"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00154"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.694"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3242872"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00191"},{"key":"ref33","first-page":"1347","article-title":"LENS: Localization enhanced by NeRF synthesis","volume-title":"Proc. Conf. Robot Learn.","author":"Moreau"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01139"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25765"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2964938"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16767"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3220270"},{"key":"ref40","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref41","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref42","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv:2203.02155"},{"key":"ref43","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref44","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref45","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref46","first-page":"1","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"You"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref48","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023","journal-title":"arXiv:2306.00890"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372832"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01428"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"ref52","article-title":"XGen-MM (BLIP-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"arXiv:2408.08872"},{"key":"ref53","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024","journal-title":"arXiv:2401.16420"},{"key":"ref54","article-title":"CogVLM: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv:2311.03079"},{"key":"ref55","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref57","article-title":"LP-SLAM: Language-perceptive RGB-D SLAM system based on large language model","author":"Zhang","year":"2023","journal-title":"arXiv:2303.10089"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3324320"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00657"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01417"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.93"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.442"},{"key":"ref63","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076556"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3034494"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71278-5_29"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00578"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412225"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318963"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10923622.pdf?arnumber=10923622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T19:08:06Z","timestamp":1742843286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10923622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3546853","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}