{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T06:56:52Z","timestamp":1790837812755,"version":"4.1.0"},"reference-count":86,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62372155"],"award-info":[{"award-number":["62372155"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Basic Research Program of Jiangsu","award":["BK20250188"],"award-info":[{"award-number":["BK20250188"]}]},{"name":"Research Funds of Jiangsu Hydraulic Research Institute","award":["2025z065"],"award-info":[{"award-number":["2025z065"]}]},{"name":"China Postdoctoral Science Foundation","award":["2025M771578"],"award-info":[{"award-number":["2025M771578"]}],"id":[{"id":"https:\/\/ror.org\/0426zh255","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3732763","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T19:11:02Z","timestamp":1790104262000},"page":"10286-10299","source":"Crossref","is-referenced-by-count":0,"title":["Making Large Vision\u2013Language Models Better Few-Shot Learners"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8724-5796","authenticated-orcid":false,"given":"Chuanyi","family":"Zhang","sequence":"first","affiliation":[{"name":"Hohai University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8746-9845","authenticated-orcid":false,"given":"Fan","family":"Liu","sequence":"additional","affiliation":[{"name":"Hohai University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2940-7620","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Hohai University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5510-4059","authenticated-orcid":false,"given":"Yuexuan","family":"An","sequence":"additional","affiliation":[{"name":"Hohai University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0814-8208","authenticated-orcid":false,"given":"Shuhua","family":"Cao","sequence":"additional","affiliation":[{"name":"Hohai University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Hohai University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109480"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0259"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01733"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02258"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00375"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02701"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref8","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V (ision)","author":"Yang","year":"2023","journal-title":"arXiv:2309.17421"},{"key":"ref9","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref10","article-title":"Lost in the middle, and in-between: Enhancing language models\u2019 ability to reason over long contexts in multi-hop qa","author":"Baker","year":"2024","journal-title":"arXiv:2412.10079"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.511"},{"key":"ref12","first-page":"19426","article-title":"Large language models are not robust multiple choice selectors","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zheng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32576"},{"key":"ref14","article-title":"Position of uncertainty: A cross-linguistic study of positional bias in large language models","author":"Mikhail","year":"2025","journal-title":"arXiv:2505.16134"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.890"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1170"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02566"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref19","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref21","first-page":"1","article-title":"VScan: Rethinking visual token reduction for efficient large vision-language models","volume-title":"Trans. Mach. Learn. Res.","author":"Zhang","year":"2026"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref27","first-page":"1","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref29","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref30","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref31","first-page":"1","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rusu"},{"issue":"1","key":"ref32","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"2","author":"Koch"},{"key":"ref33","first-page":"1","article-title":"Matching networks for one shot learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01259"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00345"},{"key":"ref40","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"issue":"240","key":"ref41","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.33"},{"key":"ref43","article-title":"InstructUIE: Multi-task instruction tuning for unified information extraction","author":"Wang","year":"2023","journal-title":"arXiv:2304.08085"},{"key":"ref44","first-page":"27168","article-title":"WizardCoder: Empowering code large language models with evol-instruct","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Luo"},{"key":"ref45","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref46","first-page":"51575","article-title":"Kosmos-2: Grounding multimodal large language models to the world","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref47","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref48","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"ref50","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049346"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00204"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369870"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02794"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01575"},{"key":"ref60","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2024.9150038"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref63","first-page":"5899","article-title":"Adaptive dimension reduction and variational inference for transductive few-shot classification","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hu"},{"key":"ref64","first-page":"50629","article-title":"Context-aware meta-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fifty"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2026.114966"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110680"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3576793"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02330"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00526"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01401"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110485"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/s24237737"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0675"},{"key":"ref77","first-page":"1","article-title":"Meta-learning with differentiable closed-form solvers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bertinetto"},{"key":"ref78","first-page":"1","article-title":"Meta-learning for semi-supervised few-shot classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ren"},{"key":"ref79","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref80","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford Dogs","volume-title":"Proc. Workshop Fine-Grained Vis. Categorization IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Khosla"},{"key":"ref81","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref84","article-title":"Qwen3-VL technical report","volume-title":"arXiv:2511.21631","author":"Bai","year":"2025"},{"key":"ref85","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":"ref86","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"arXiv:2308.01390"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11703943.pdf?arnumber=11703943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T06:16:30Z","timestamp":1790835390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11703943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3732763","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}