{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:05:38Z","timestamp":1780052738793,"version":"3.53.1"},"reference-count":53,"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":[{"DOI":"10.13039\/100018996","name":"HEAL-Link","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018996","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3579420","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T17:52:20Z","timestamp":1749837140000},"page":"106155-106174","source":"Crossref","is-referenced-by-count":4,"title":["When Multimodal Large Language Models Meet Computer Vision: Progressive GPT Fine-Tuning and Stress Testing"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8098-1616","authenticated-orcid":false,"given":"Konstantinos I.","family":"Roumeliotis","sequence":"first","affiliation":[{"name":"Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of Peloponnese, Tripoli, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5799-3558","authenticated-orcid":false,"given":"Nikolaos D.","family":"Tselikas","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of Peloponnese, Tripoli, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7386-1029","authenticated-orcid":false,"given":"Dimitrios K.","family":"Nasiopoulos","sequence":"additional","affiliation":[{"name":"Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3040649"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00542"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21917\/ijivp.2020.0317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3152247"},{"key":"ref8","volume-title":"Introducing Vision to the Fine-tuning API | OpenAI","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icdm.2011.79"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11419"},{"key":"ref11","article-title":"A multimodal late fusion model for e-commerce product classification","author":"Bi","year":"2020","journal-title":"arXiv:2008.06179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467164"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-74127-2_8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50347-5_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3231742"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iccmc51019.2021.9418371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/assp54407.2021.00025"},{"key":"ref18","volume-title":"A Scalable Framework for Product Image Classification Applied To Home Improvement E-Commerce","author":"Xu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102963"},{"key":"ref20","article-title":"RetailKLIP: Finetuning OpenCLIP backbone using metric learning on a single GPU for zero-shot retail product image classification","author":"Srivastava","year":"2023","journal-title":"arXiv:2312.10282"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ispa54004.2022.9786364"},{"key":"ref22","volume-title":"Semi-supervised Learning and Visual Transformers for Product Attribute Extraction from E-Commerce Images","author":"Impata","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3020737"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09079-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57426-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681488"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3425953"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s23229225"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_18"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3688005"},{"key":"ref31","volume-title":"Introducing Computer Use, a New Claude 3.5 Sonnet, and Claude 3.5 Haiku Anthropic","year":"2025"},{"key":"ref32","volume-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref33","article-title":"MM-VID: Advancing video understanding with GPT-4 V(ision)","author":"Lin","year":"2023","journal-title":"arXiv:2310. 19773"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3477090"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102367"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2024.110101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-89328-y"},{"key":"ref38","volume-title":"Applied-AI-Research-Lab\/When-Large-Language-Models-Meet-Computer-Vision-GPT-4o-Vision-Model-Progressive-Fine-Tuning? GitHub","year":"2024"},{"key":"ref39","volume-title":"Amazon Products Dataset 2023 (1.4M Products)","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/elinfocom.2019.8706476"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2890127"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/igarss.2018.8517574"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iemtronics51293.2020.9216455"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.inpa.2025.03.001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1117\/12.2671201"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/itaic58329.2023.10409019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2025.3534474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/idciot64235.2025.10914815"},{"key":"ref50","volume-title":"Automatically Generate First Draft Prompt Templates\u2014Anthropic","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.04.142"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106664"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi9080478"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11036181.pdf?arnumber=11036181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T06:05:58Z","timestamp":1750831558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11036181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3579420","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}