{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T10:48:52Z","timestamp":1773571732086,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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","award":["62301385"],"award-info":[{"award-number":["62301385"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471394"],"award-info":[{"award-number":["62471394"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2041"],"award-info":[{"award-number":["U21B2041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604977","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:46:51Z","timestamp":1757353611000},"page":"7905-7916","source":"Crossref","is-referenced-by-count":3,"title":["Like Humans to Few-Shot Learning Through Knowledge Permeation of Visual and Language"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2303-8995","authenticated-orcid":false,"given":"Yuyu","family":"Jia","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3300-0805","authenticated-orcid":false,"given":"Qing","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6736-3389","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-4956","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3039329"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3394681"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3453055"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3295129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3253054"},{"key":"ref6","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn","year":"2017"},{"key":"ref7","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref8","article-title":"Meta-learning with latent embedding optimization","author":"Rusu","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01733"},{"key":"ref10","first-page":"21981","article-title":"CrossTransformers: Spatially-aware few-shot transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Doersch","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093338"},{"key":"ref12","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3123813"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref19","first-page":"4847","article-title":"Adaptive cross-modal few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Xing","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463641"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02258"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01892"},{"key":"ref25","first-page":"14542","article-title":"Channel importance matters in few-shot image classification","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Luo","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref29","article-title":"Gaussian prototypical networks for few-shot learning on omniglot","author":"Fort","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_15"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3492045"},{"key":"ref32","article-title":"BOIL: Towards representation change for few-shot learning","author":"Oh","year":"2020"},{"key":"ref33","first-page":"7693","article-title":"Fast context adaptation via meta-learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Zintgraf","year":"2019"},{"key":"ref34","article-title":"Contrastive meta-learning for partially observable few-shot learning","author":"Jelley","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3443534"},{"key":"ref36","first-page":"3582","article-title":"Rethinking generalization in few-shot classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hiller","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_43"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_17"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3307149"},{"key":"ref40","article-title":"Subspace regularizers for few-shot class incremental learning","author":"Akyrek","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01259"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00053"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687683"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref51","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin","year":"2021"},{"key":"ref52","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"ref54","first-page":"883","article-title":"Learning to explain: An information-theoretic perspective on model interpretation","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Chen","year":"2018"},{"key":"ref55","article-title":"Meta-learning for semi-supervised few-shot classification","author":"Ren","year":"2018"},{"key":"ref56","article-title":"Meta-learning with differentiable closed-form solvers","author":"Bertinetto","year":"2018"},{"key":"ref57","first-page":"719","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Oreshkin","year":"2018"},{"key":"ref58","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref59","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref60","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref61","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00815"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_2"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00832"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00881"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01085"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02701"},{"key":"ref72","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","author":"Triantafillou","year":"2019"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28614"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00069"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00829"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00857"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00891"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"ref80","article-title":"SimpleShot: Revisiting nearest-neighbor classification for few-shot learning","author":"Wang","year":"2019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00021"},{"key":"ref82","first-page":"21073","article-title":"Alleviating the sample selection bias in few-shot learning by removing projection to the centroid","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xu","year":"2022"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11153060.pdf?arnumber=11153060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:19Z","timestamp":1761153919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604977","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}