{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T20:17:34Z","timestamp":1778876254789,"version":"3.51.4"},"reference-count":42,"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":[{"DOI":"10.13039\/100014462","name":"Mitsubishi Electric Research Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014462","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3687477","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:48:59Z","timestamp":1777405739000},"page":"70724-70736","source":"Crossref","is-referenced-by-count":0,"title":["GPT Sonography: Hand Gesture Decoding From Forearm Ultrasound Images via a Large Vision-Language Model"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3735-7700","authenticated-orcid":false,"given":"Keshav","family":"Bimbraw","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5220-1830","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2578-5372","authenticated-orcid":false,"given":"Toshiaki","family":"Koike-Akino","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref2","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app14177782"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000001754"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2024.114132"},{"key":"ref8","article-title":"Diagnostic performances of GPT-4o, Claude 3 Opus, and Gemini 1.5 pro in radiology\u2019s diagnosis please cases","author":"Sonoda","year":"2024","journal-title":"MedRxiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-024-01633-0"},{"key":"ref10","article-title":"Empowering radiologists with ChatGPT-4o: Comparative evaluation of large language models and radiologists in cardiac cases","author":"Cesur","year":"2024","journal-title":"MedRxiv"},{"key":"ref11","volume-title":"Sonography: Principles and Instruments","author":"Kremkau","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2023.3237774"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025807"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3203084"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC44109.2020.9176483"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BSN58485.2023.10331075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1117\/12.3005247"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2498124"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2015.7281166"},{"key":"ref20","article-title":"Fine-tuning large vision-language models as decision-making agents via reinforcement learning","author":"Zhai","year":"2024","journal-title":"arXiv:2405.10292"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref22","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00356"},{"key":"ref25","first-page":"625","article-title":"Can vision-language models be a good guesser? Exploring VLMs for times and location reasoning","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03017-3_10"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.101"},{"key":"ref28","volume-title":"4L Linear Palm Doppler Ultrasound Probe","year":"2024"},{"key":"ref29","volume-title":"GitHub-OpenAI\/OpenAI-Python: The Official Python Library for the OpenAI API","year":"2024"},{"key":"ref30","volume-title":"Uploading Base-64 Encoded Images","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref33","first-page":"2585","article-title":"Instruct me more! Random prompting for visual in-context learning","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref35","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"ref37","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref38","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv:2502.14786"},{"key":"ref39","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv:2402.00253"},{"key":"ref40","volume-title":"Stacks|Radiology Reference Article|Radiopaedia","author":"Gaillard","year":"2024"},{"key":"ref41","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref42","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024","journal-title":"arXiv:2403.14608"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11494645.pdf?arnumber=11494645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T19:55:05Z","timestamp":1778874905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11494645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3687477","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}