{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:14:51Z","timestamp":1781018091793,"version":"3.54.1"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","award":["IPCEI-CL0000007"],"award-info":[{"award-number":["IPCEI-CL0000007"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01521","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16388-16398","source":"Crossref","is-referenced-by-count":2,"title":["On Large Multimodal Models as Open-World Image Classifiers"],"prefix":"10.1109","author":[{"given":"Alessandro","family":"Conti","sequence":"first","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Massimiliano","family":"Mancini","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrico","family":"Fini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Rota","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.12.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref7","article-title":"Are we done with imagenet?","author":"Beyer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref9","article-title":"Mllm-as-a-judge: Assessing multimodal llm-as-a-judge with vision-language benchmark","author":"Chen","year":"2024","journal-title":"ICML"},{"key":"ref10","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref14","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 \\%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref15","article-title":"Chatbot arena: An open platform for evaluating 11 ms by human preference","author":"Chiang","year":"2024","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1337"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92648-8_12"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02284"},{"issue":"8","key":"ref21","first-page":"242","article-title":"Arpad E Elo. The proposed uscf rating system, its development, theory, and applications","volume":"22","year":"1967","journal-title":"Chess life"},{"key":"ref22","article-title":"Domino: Discovering systematic errors with cross-modal embeddings","author":"Eyuboglu","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2004.383"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref25","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1355"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755316"},{"key":"ref29","volume-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01054"},{"key":"ref31","first-page":"17283","article-title":"Grounding language models to images for multimodal inputs and outputs","volume-title":"International Conference on Machine Learning","author":"Koh","year":"2023"},{"key":"ref32","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2022","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref34","volume-title":"What matters when building vision-language models? NeurIPS","author":"Lauren\u00e7on","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref36","volume-title":"Llava-next: Stronger llms supercharge multimodal capabilities in the wild","author":"Li","year":"2024"},{"key":"ref37","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref42","article-title":"Revisiting mllms: An in-depth analysis of image classification abilities","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref44","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Hard imagenet: Segmentations for objects with strong spurious cues","author":"Moayeri","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref47","article-title":"Cats and dogs","author":"Omkar","year":"2012","journal-title":"CVPR"},{"key":"ref48","article-title":"Automated classification of model errors on imagenet","author":"Peychev","year":"2023","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref52","article-title":"Testtime prompt tuning for zero-shot generalization in visionlanguage models","author":"Shu","year":"2022","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref54","article-title":"Salient imagenet: How to discover spurious features in deep learning?","author":"Singla","year":"2022","journal-title":"ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01266"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref57","article-title":"Llamavo1: Rethinking step-by-step visual reasoning in 11 ms","author":"Thawakar","year":"2025","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"When does dough become a bagel? analyzing the remaining mistakes on imagenet","author":"Vasudevan","year":"2022","journal-title":"NeurIPS"},{"key":"ref60","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref63","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00442"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_21"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01575"},{"key":"ref67","article-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?","author":"Yuksekgonul","year":"2023","journal-title":"ICLR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref69","article-title":"Why are visually-grounded language models bad at image classification?","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref70","article-title":"Minigpt5: Interleaved vision-and-language generation via generative vokens","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref73","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2024","journal-title":"ICLR"},{"key":"ref74","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024","journal-title":"ICLR"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443475.pdf?arnumber=11443475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:12Z","timestamp":1777612452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443475\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01521","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}