{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:05:14Z","timestamp":1767773114612,"version":"build-2065373602"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209018","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Fine-tuned Multimodal Large Language Models are Zero-shot Learners in Image Quality Assessment"],"prefix":"10.1109","author":[{"given":"Rui","family":"Xiong","sequence":"first","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhida","family":"Feng","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shikun","family":"Feng","sequence":"additional","affiliation":[{"name":"Baidu Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"A survey on iqa","year":"2022","author":"Wang","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/pcs50896.2021.9477470"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9948927"},{"key":"ref5","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","year":"2023","author":"Chiang","key":"ref11"},{"article-title":"Mistral 7b","year":"2023","author":"Jiang","key":"ref12"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref13"},{"article-title":"Minicpm-v: A gpt-4v level mllm on your phone","year":"2024","author":"Yao","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"article-title":"Kosmos-2: Grounding multimodal large language models to the world","year":"2023","author":"Peng","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3171445"},{"key":"ref19","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"article-title":"Faster segment anything: Towards lightweight sam for mobile applications","year":"2023","author":"Zhang","key":"ref20"},{"article-title":"Pandagpt: One model to instruction-follow them all","year":"2023","author":"Su","key":"ref21"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1117\/1.3267105"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2053549"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3319020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209018.pdf?arnumber=11209018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:20Z","timestamp":1761888620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209018","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}