{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:35:57Z","timestamp":1778081757641,"version":"3.51.4"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00097","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"927-937","source":"Crossref","is-referenced-by-count":2,"title":["DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Hongjin","family":"Zhao","sequence":"first","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihao","family":"Li","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyue","family":"Qin","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge-Peng","family":"Ji","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Gedeon","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Barnes","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref4","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref5","volume-title":"Cosmetic dermatology","author":"Baumann","year":"2009"},{"key":"ref6","volume-title":"Dermatology","author":"Braun-Falco","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"issue":"3","key":"ref9","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref10","article-title":"Visionqaries at mediqa-magic 2024: Small vision language models for dermatological diagnosis","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction, Proceedings of the 15th International Conference of the CLEF Association (CLEF 2024), Springer Lecture Notes in Computer Science LNCS","author":"Cieplicka"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20078"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0795"},{"key":"ref13","first-page":"209","article-title":"Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model","volume-title":"Machine Learning for Health","author":"Endo","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/dermato4040013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2196\/49280"},{"key":"ref16","article-title":"Clinkd: Cross-modal clinical knowledge distiller for multi-task medical images","author":"Ge","year":"2025"},{"key":"ref17","author":"Ge","year":"2025","journal-title":"Clinkd: Cross-modal clinic knowledge distiller for multi-task medical images"},{"key":"ref18","volume-title":"Dermnet skin disease dataset","author":"Goel","year":"2022"},{"key":"ref19","volume-title":"Clinical dermatology E-book","author":"Habif","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1430984"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref23","author":"Ilharco","year":"2021","journal-title":"Open-clip"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1597-6"},{"key":"ref25","article-title":"Colon-x: Advancing intelligent colonoscopy from multi-modal understanding to clinical reasoning","author":"Ji","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0004"},{"key":"ref27","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref28","volume-title":"Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models","author":"Jurafsky","year":"2000"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref31","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2014.7064414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref34","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref35","author":"Liu","year":"2023","journal-title":"Improved baselines with visual instruction tuning"},{"key":"ref36","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref37","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref38","author":"Liu","year":"2023","journal-title":"Qilin-med-vl: Towards chinese large vision-language model for general healthcare"},{"key":"ref39","article-title":"Gpteval: Nlg evaluation using gpt-4 with better human alignment","author":"Liu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2024.100099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1163\/3050-7642_ejtc_macro036"},{"key":"ref42","first-page":"43136","article-title":"Fairness-guided few-shot prompting for large language models","volume-title":"Advances in Neural Information Processing Systems","author":"Ma","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_69"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881948"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.32"},{"key":"ref46","article-title":"Capabilities of gpt-4 on medical challenge problems","author":"Nori","year":"2023"},{"key":"ref47","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni"},{"key":"ref48","first-page":"2024","article-title":"Evaluating the diagnostic and treatment recommendation capabilities of gpt-4 vision in dermatology","author":"Pillai","year":"2024","journal-title":"medRxiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00108"},{"key":"ref50","article-title":"Gpt4point: A unified framework for point-language understanding and generation","author":"Qi","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.135"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2010.316"},{"key":"ref56","year":"2023","journal-title":"Internlm: A multilingual language model with progressively enhanced capabilities"},{"key":"ref57","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref58","year":"2022","journal-title":"Bald people dataset"},{"key":"ref59","article-title":"Crowdsourcing dermatology images with google search ads: Creating a real-world skin condition dataset","author":"Ward","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01074"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref62","article-title":"Advancing multimodal medical capabilities of gemini","author":"Yang","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72086-4_20"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3698587.3701359"},{"issue":"3","key":"ref65","first-page":"6","article-title":"Large-scale domain-specific pre-training for biomedical vision-language processing","volume":"2","author":"Zhang","year":"2023"},{"key":"ref66","article-title":"Facephi: Lightweight multimodal large language model for facial landmark emotion recognition","volume-title":"5th Workshop on practical ML for limited\/low resource settings","author":"Zhao"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50043-3"},{"key":"ref68","article-title":"Skincap: A multi-modal dermatology dataset annotated with rich medical captions","author":"Zhou","year":"2024"},{"key":"ref69","first-page":"6625","article-title":"Benchx: A unified benchmark framework for medical vision-language pretraining on chest x-rays","volume":"37","author":"Zhou","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref70","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492571.pdf?arnumber=11492571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:58:09Z","timestamp":1778047089000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00097","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}