{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T13:02:51Z","timestamp":1769778171428,"version":"3.49.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union Horizon\u2013Research and Innovation Framework Programme through the VANGUARD Project","award":["101121282"],"award-info":[{"award-number":["101121282"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3656619","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:11:10Z","timestamp":1769029870000},"page":"13202-13217","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Source Visual Language Model Fusion for Indoor Geolocation Reliability"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9397-8159","authenticated-orcid":false,"given":"Nikolaos","family":"Konstantinou","sequence":"first","affiliation":[{"name":"Visual Computing Laboratory, Centre for Research and Technology Hellas, Thermi–Panorama, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6825-4328","authenticated-orcid":false,"given":"Theodoros","family":"Semertzidis","sequence":"additional","affiliation":[{"name":"Visual Computing Laboratory, Centre for Research and Technology Hellas, Thermi–Panorama, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3814-6710","authenticated-orcid":false,"given":"Petros","family":"Daras","sequence":"additional","affiliation":[{"name":"Visual Computing Laboratory, Centre for Research and Technology Hellas, Thermi–Panorama, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301726"},{"key":"ref2","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3007540.3007547"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1140\/epjds\/s13688-019-0182-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref7","first-page":"379","article-title":"GeoCLIP: Clip-inspired alignment between locations and images for effective worldwide geo-localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cepeda"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01225"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3408075"},{"key":"ref11","article-title":"Multimodal large language models to support real-world fact-checking","author":"Geng","year":"2024","journal-title":"arXiv:2403.03627"},{"key":"ref12","article-title":"Language models (mostly) know what they know","author":"Kadavath","year":"2022","journal-title":"arXiv:2207.05221"},{"key":"ref13","article-title":"Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Kuhn"},{"key":"ref14","article-title":"Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language models","author":"Duan","year":"2023","journal-title":"arXiv:2307.01379"},{"key":"ref15","first-page":"3095","article-title":"Unveiling uncertainty: A deep dive into calibration and performance of multimodal large language models","volume-title":"Proc. 31st Int. Conf. Comput. Linguistics","author":"Chen"},{"key":"ref16","article-title":"Uncertainty-aware evaluation for vision-language models","author":"Kostumov","year":"2024","journal-title":"arXiv:2402.14418"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.74"},{"key":"ref18","article-title":"Can LLMs express their uncertainty? An empirical evaluation of confidence elicitation in LLMs","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xiong"},{"key":"ref19","article-title":"Llamas know what GPTs don\u2019t show: Surrogate models for confidence estimation","author":"Shrivastava","year":"2023","journal-title":"arXiv:2311.08877"},{"key":"ref20","article-title":"Generating with confidence: Uncertainty quantification for black-box large language models","author":"Lin","year":"2023","journal-title":"arXiv:2305.19187"},{"key":"ref21","article-title":"Image-based geolocation using large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv:2408.09474"},{"key":"ref22","article-title":"Evaluating precise geolocation inference capabilities of vision language models","author":"Jay","year":"2025","journal-title":"arXiv:2502.14412"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01032"},{"key":"ref24","article-title":"An empirical study into what matters for calibrating vision-language models","author":"Tu","year":"2024","journal-title":"arXiv:2402.07417"},{"key":"ref25","first-page":"23429","article-title":"Calibrating multimodal learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610333"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.4000\/abe.10839","article-title":"Buenos aires (1880\u20131960). Transferts techniques et culturels","volume":"7","author":"Bechini","year":"2015","journal-title":"ABE J."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775151"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102430"},{"key":"ref31","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume-title":"Advances in Large Margin Classifiers","author":"Platt","year":"1999"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587784"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.286"},{"key":"ref34","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lundberg"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11359628.pdf?arnumber=11359628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:25:31Z","timestamp":1769721931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3656619","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}