{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T02:01:57Z","timestamp":1777514517271,"version":"3.51.4"},"reference-count":67,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministry of Economic Development of the Russian Federation","award":["139-15-2025-013"],"award-info":[{"award-number":["139-15-2025-013"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3618728","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:49:41Z","timestamp":1759859381000},"page":"177098-177110","source":"Crossref","is-referenced-by-count":3,"title":["MSSPlace: Multi-Sensor Place Recognition With Visual and Text Semantics"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5721-5073","authenticated-orcid":false,"given":"Alexander","family":"Melekhin","sequence":"first","affiliation":[{"name":"Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1407-2633","authenticated-orcid":false,"given":"Dmitry A.","family":"Yudin","sequence":"additional","affiliation":[{"name":"Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilia","family":"Petryashin","sequence":"additional","affiliation":[{"name":"Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vitaly","family":"Bezuglyj","sequence":"additional","affiliation":[{"name":"Moscow Institute of Physics and Technology, Dolgoprudny, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/603"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3343602"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00183"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956458"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19934"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178797"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00799"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3267693"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s20102870"},{"key":"ref14","article-title":"PIC-Net: Point cloud and image collaboration network for large-scale place recognition","author":"Lu","year":"2020","journal-title":"arXiv:2008.00658"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561078"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635839"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3210880"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3176731"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104152"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981266"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892761"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981113"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.065"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00657"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/mti6110102"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25347"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref30","article-title":"Real-time kinematic ground truth for the Oxford RobotCar dataset","author":"Maddern","year":"2020","journal-title":"arXiv:2002.10152"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915614638"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref33","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref34","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref35","article-title":"BEVPlace++: Fast, robust, and lightweight LiDAR global localization for unmanned ground vehicles","author":"Luo","year":"2024","journal-title":"arXiv:2408.01841"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00292"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV50220.2020.9305429"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611563"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00012"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043875"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06430-2_38"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06087-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9354909"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01683"},{"key":"ref47","article-title":"Objects matter: Learning object relation graph for robust camera relocalization","author":"Qiao","year":"2022","journal-title":"arXiv:2205.13280"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.022"},{"key":"ref49","article-title":"Learning local features with context aggregation for visual localization","author":"Hong","year":"2020","journal-title":"arXiv:2005.12880"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/UR55393.2022.9826253"},{"key":"ref51","article-title":"WildRefer: 3D object localization in large-scale dynamic scenes with multi-modal visual data and natural language","author":"Lin","year":"2023","journal-title":"arXiv:2304.05645"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC55077.2022.9886770"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref55","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref56","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00470"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref63","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":"ref64","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv:2310.07704"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560932"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00604"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.4310\/cis.2023.v23.n1.a3"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11195136.pdf?arnumber=11195136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:42:34Z","timestamp":1760722954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3618728","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}