{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:32:29Z","timestamp":1793205149211,"version":"4.5.0"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["62076004"],"award-info":[{"award-number":["62076004"]}],"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":["62102205"],"award-info":[{"award-number":["62102205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2108085Y23"],"award-info":[{"award-number":["2108085Y23"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Provincial Key Research and Development Program","award":["2022i01020014"],"award-info":[{"award-number":["2022i01020014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcsvt.2023.3282777","type":"journal-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T14:01:54Z","timestamp":1685973714000},"page":"7789-7802","source":"Crossref","is-referenced-by-count":110,"title":["Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8510-0964","authenticated-orcid":false,"given":"Xixi","family":"Wang","sequence":"first","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-1596","authenticated-orcid":false,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1414-3307","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3116349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3271218"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/rs15020331"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3174072"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.03.022"},{"key":"ref7","first-page":"6907","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Rusu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076523"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3241651"},{"key":"ref13","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref14","first-page":"2952","article-title":"Scalable gradient-based tuning of continuous regularization hyperparameters","volume-title":"Proc. IEEE\/CVF Int. Conf. Mach. Learn.","author":"Luketina"},{"key":"ref15","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. IEEE\/CVF Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref16","article-title":"Few-shot learning via embedding adaptation with set-to-set functions","author":"Ye","year":"2018","journal-title":"arXiv:1812.03664"},{"key":"ref17","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML","author":"Raghu","year":"2019","journal-title":"arXiv:1909.09157"},{"key":"ref18","first-page":"1","article-title":"Meta-learning update rules for unsupervised representation learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Metz"},{"key":"ref19","first-page":"3664","article-title":"Rapid adaptation with conditionally shifted neurons","volume-title":"Proc. IEEE\/CVF Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"ref21","first-page":"113","article-title":"Meta-learning with implicit gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rajeswaran"},{"key":"ref22","first-page":"3314","article-title":"Meta-curvature","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Park"},{"key":"ref23","first-page":"10276","article-title":"Learning to self-train for semi-supervised few-shot classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref24","article-title":"How to train your MAML","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Antoniou"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref26","article-title":"Meta-learning with warped gradient descent","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Flennerhag"},{"key":"ref27","first-page":"8","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. ICML Deep Learn. Workshop","volume":"2","author":"Koch"},{"key":"ref28","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Snell"},{"key":"ref29","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"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"ref32","article-title":"A closer look at few-shot classification","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3132912"},{"key":"ref35","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00891"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01415"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref41","article-title":"HyperTransformer: Model generation for supervised and semi-supervised few-shot learning","author":"Zhmoginov","year":"2022","journal-title":"arXiv:2201.04182"},{"key":"ref42","first-page":"4003","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hou"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995754"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00781"},{"key":"ref45","article-title":"Learning to propagate labels: Transductive propagation network for few-shot learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00676"},{"key":"ref47","first-page":"21981","article-title":"CrossTransformers: Spatially-aware few-shot transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Doersch"},{"key":"ref48","article-title":"Semantic cross attention for few-shot learning","author":"Xiao","year":"2022","journal-title":"arXiv:2210.06311"},{"key":"ref49","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3150169"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202563"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"ref56","first-page":"1992","article-title":"TransMatcher: Deep image matching through transformers for generalizable person re-identification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liao"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141267"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref59","article-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021","journal-title":"arXiv:2107.10834"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148867"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref65","article-title":"A universal representation transformer layer for few-shot image classification","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3155991"},{"key":"ref67","first-page":"1","article-title":"MELR: Meta-learning via modeling episode-level relationships for few-shot learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Fei"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.074"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3147198"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/sapm1941201224"},{"key":"ref72","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.070"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00042"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00948"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00011"},{"key":"ref80","first-page":"1","article-title":"Meta-learning for semi-supervised few-shot classification","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Ren"},{"key":"ref81","volume-title":"The Caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref83","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ravi"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.02.073"},{"key":"ref86","article-title":"IEPT: Instance-level and episode-level pretext tasks for few-shot learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref87","first-page":"7510","article-title":"Meta variance transfer: Learning to augment from the others","volume-title":"Proc. IEEE\/CVF Int. Conf. Mach. Learn.","author":"Park"},{"key":"ref88","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. IEEE\/CVF Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref89","article-title":"Deep meta-learning: Learning to learn in the concept space","author":"Zhou","year":"2018","journal-title":"arXiv:1802.03596"},{"key":"ref90","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu"},{"issue":"11","key":"ref91","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10348119\/10144072.pdf?arnumber=10144072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T20:16:21Z","timestamp":1703016981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10144072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":91,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3282777","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}