{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T11:07:30Z","timestamp":1774782450140,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0118801"],"award-info":[{"award-number":["2022ZD0118801"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG2-RP-2021-022"],"award-info":[{"award-number":["AISG2-RP-2021-022"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3379896","type":"journal-article","created":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T18:30:49Z","timestamp":1711045849000},"page":"8543-8556","source":"Crossref","is-referenced-by-count":9,"title":["Fine-Tuning for Few-Shot Image Classification by Multimodal Prototype Regularization"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6939-4357","authenticated-orcid":false,"given":"Qianhao","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7127-7400","authenticated-orcid":false,"given":"Jiaxin","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4543-2179","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref5","first-page":"29914","article-title":"Segment anything in high quality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke","year":"2023"},{"key":"ref6","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2855081"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref11","first-page":"1","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3033124"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"ref17","first-page":"1","article-title":"Revisit finetuning strategy for few-shot learning to transfer the emdeddings","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993952"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25496"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1980-0572855-7"},{"key":"ref22","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","first-page":"1","article-title":"An image is worth 1616 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref31","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref33","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Socher","year":"2013"},{"key":"ref34","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frome","year":"2013"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref36","first-page":"921","article-title":"The importance of encoding versus training with sparse coding and vector quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Coates","year":"2011"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_56"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.321"},{"key":"ref39","article-title":"Boundary and relation distillation for semantic segmentation","author":"Zhang","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"ref41","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.218"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.449"},{"key":"ref46","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref48","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref49","first-page":"2022","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref50","article-title":"Florence: A. new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref51","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref52","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"issue":"8","key":"ref55","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108594"},{"key":"ref57","first-page":"30146","article-title":"BLIP-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01857"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25363"},{"key":"ref61","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals","year":"2016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3590-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3173687"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01928-1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233442"},{"key":"ref67","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547858"},{"key":"ref69","first-page":"1","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Rusu","year":"2019"},{"key":"ref70","first-page":"1","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Ravi","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3227574"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_37"},{"key":"ref74","first-page":"2022","article-title":"On the importance of firth bias reduction in few-shot classification","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Ghaffari"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2005.09.012"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref82","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref84","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10476759.pdf?arnumber=10476759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:03:30Z","timestamp":1725249810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476759\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3379896","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}