{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:15:37Z","timestamp":1773155737345,"version":"3.50.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s13042-024-02189-1","type":"journal-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T09:09:45Z","timestamp":1715418585000},"page":"4747-4759","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Local descriptor-based spatial cross attention network for few-shot learning"],"prefix":"10.1007","volume":"15","author":[{"given":"Jiamin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5844","authenticated-orcid":false,"given":"Lina","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"2189_CR1","doi-asserted-by":"crossref","unstructured":"LeCun Y, Bengio Y, Hinton G. (2015) Deep learning. In: Nature, pp 436\u2013444","DOI":"10.1038\/nature14539"},{"key":"2189_CR2","doi-asserted-by":"crossref","unstructured":"Krizhevsky A, Sutskever I, Hinton G E. (2017) ImageNet classification with deep convolutional neural networks. In: Communications of the ACM, pp 84\u201390","DOI":"10.1145\/3065386"},{"key":"2189_CR3","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, et al. (2009) ImageNet: a large-scale hierarchical image database. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2189_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy C, Wei Liu, Yangqing Jia, et al. (2015) Going deeper with convolutions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2189_CR5","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2189_CR6","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, et al. (2017) Densely connected convolutional networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2261\u20132269","DOI":"10.1109\/CVPR.2017.243"},{"key":"2189_CR7","doi-asserted-by":"crossref","unstructured":"Li W, Liu X, Yuan Y. (2022) SIGMA: semantic-complete graph matching for domain adaptive object detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5281\u20135290","DOI":"10.1109\/CVPR52688.2022.00522"},{"key":"2189_CR8","doi-asserted-by":"crossref","unstructured":"K. Hu J, Kuai T, Waslander S. (2022) Point density-aware voxels for LiDAR 3D object detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8459\u20138468","DOI":"10.1109\/CVPR52688.2022.00828"},{"key":"2189_CR9","doi-asserted-by":"crossref","unstructured":"Zhang X, Xu H, Mo H, et al. (2021) DCNAS: densely connected neural architecture search for semantic image segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13951\u201313962","DOI":"10.1109\/CVPR46437.2021.01374"},{"key":"2189_CR10","doi-asserted-by":"crossref","unstructured":"Kim N, Kim D, Kwak S, et al. (2022) ReSTR: convolution-free referring image segmentation using transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 18124\u201318133","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"2189_CR11","doi-asserted-by":"crossref","unstructured":"Lee S, Seong H, Lee S, et al. (2022) Correlation verification for image retrieval. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5364\u20135374","DOI":"10.1109\/CVPR52688.2022.00530"},{"key":"2189_CR12","unstructured":"Yan C, Gong B, Wei Y, et al. (2020) Deep multi-view enhancement hashing for image retrieval. arXiv"},{"key":"2189_CR13","unstructured":"Wang J, Sun K, Cheng T, et al. (2020) Deep high-resolution representation learning for visual recognition. arXiv"},{"key":"2189_CR14","doi-asserted-by":"crossref","unstructured":"Ding K, Xu Z, Tong H, et al. (2022) Data augmentation for deep graph learning: a survey. In: ACM SIGKDD Explorations Newsletter, pp 61\u201377","DOI":"10.1145\/3575637.3575646"},{"key":"2189_CR15","unstructured":"Ioffe S, Szegedy C (2022) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:2202.08235"},{"key":"2189_CR16","unstructured":"Kuka\u010dka J, Golkov V, Cremers D (2017) Regularization for deep learning: a taxonomy. arXiv:1710.10686"},{"key":"2189_CR17","doi-asserted-by":"crossref","unstructured":"Sun Q, Liu Y, Chua T-S, et al. (2019) Meta-transfer learning for few-shot learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 403\u2013412","DOI":"10.1109\/CVPR.2019.00049"},{"key":"2189_CR18","doi-asserted-by":"crossref","unstructured":"Baik S, Hong S, Lee K M (2020) Learning to forget for meta-learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2376\u20132384","DOI":"10.1109\/CVPR42600.2020.00245"},{"key":"2189_CR19","doi-asserted-by":"crossref","unstructured":"Simon C, Koniusz P, Nock R, et al. (2020) Adaptive subspaces for few-shot learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4135\u20134144","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"2189_CR20","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML"},{"key":"2189_CR21","doi-asserted-by":"crossref","unstructured":"Ye H-J, Hu H, Zhan D-C, et al. (2020) Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8805\u20138814","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"2189_CR22","unstructured":"Zhang C, Cai Y, Lin G, et al. (2020) DeepEMD: differentiable earth mover\u2019s distance for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12203\u201312213"},{"key":"2189_CR23","doi-asserted-by":"crossref","unstructured":"Li W, Wang L, Xu J, et al. (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7253\u20137260","DOI":"10.1109\/CVPR.2019.00743"},{"key":"2189_CR24","doi-asserted-by":"crossref","unstructured":"He J, Hong R, Liu X, et al. (2022) Revisiting local descriptor for improved few-shot classification. In: ACM Transactions on Multimedia Computing, Communications, and Applications, pp 1\u201323","DOI":"10.1145\/3511917"},{"key":"2189_CR25","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Neural Information Processing Systems, pp 4077\u20134087"},{"key":"2189_CR26","unstructured":"Oreshkin BN, Lopez PR, Lacoste A. (2018) TADAM: task dependent adaptive metric for improved few-shot learning. In: Neural Information Processing Systems, pp 721\u2013731"},{"key":"2189_CR27","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, et al. (2018) Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"2189_CR28","unstructured":"Kwonjoon L, Subhransu M, Avinash R, et al. (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10657\u201310665"},{"key":"2189_CR29","unstructured":"Hou R, Chang H, Ma B, et al. (2019) Cross attention network for few-shot classification. In: Neural Information Processing Systems, pp 4005\u20134016"},{"key":"2189_CR30","unstructured":"Jiang Z, Kang B, Zhou K, et al. (2020) Few-shot classification via adaptive attention. arXiv:2008.02465"},{"key":"2189_CR31","unstructured":"Zhmoginov A, Sandler M, Vladymyrov M. (2022) HyperTransformer: model generation for supervised and semi-supervised few-shot learning. arXiv:2201.04182."},{"key":"2189_CR32","doi-asserted-by":"crossref","unstructured":"He Y, Liang W, Zhao D, et al. (2022) Attribute surrogates learning and spectral tokens pooling in transformers for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9109\u20139119","DOI":"10.1109\/CVPR52688.2022.00891"},{"key":"2189_CR33","unstructured":"Doersch C, Gupta A, Zisserman A. (2020) CrossTransformers: spatially-aware few-shot transfer. In: Neural Information Processing Systems, pp 21981\u201321993"},{"key":"2189_CR34","doi-asserted-by":"crossref","unstructured":"Tian Y, Wang Y, Krishnan D, et al. (2020) Rethinking few-shot image classification: a good embedding is all you need? arXiv:2003.11539","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"2189_CR35","unstructured":"Dhillon G, Chaudhari P, Ravichandran A, et al. (2019) A baseline for few-shot image classification. arXiv:1909.02729"},{"key":"2189_CR36","unstructured":"Chen W, Liu Y, Kira Z, et al. (2019) A closer look at few-shot classification. In: International Conference on Learning Representations"},{"key":"2189_CR37","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu C, Liu C, et al. (2020) Instance credibility inference for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 12833\u201312842","DOI":"10.1109\/CVPR42600.2020.01285"},{"key":"2189_CR38","unstructured":"Vinyals O, Blundell C, Lillicrap T, et al. (2016) Matching networks for one shot learning. In: Neural Information Processing Systems, pp 3630\u20133638"},{"key":"2189_CR39","unstructured":"Ren M, Triantafillou E, Ravi S, et al. (2018) Meta-learning for semi-supervised few-shot classification. arXiv:1803.00676"},{"key":"2189_CR40","unstructured":"Bertinetto L, Henriques J F, Torr P H S, et al. (2018) Meta-learning with differentiable closed-form solvers. arXiv:1805.08136"},{"key":"2189_CR41","unstructured":"Russakovsky O, Deng J, Su H, et al. (2014) ImageNet large scale visual recognition challenge. arXiv:1409.0575"},{"key":"2189_CR42","doi-asserted-by":"crossref","unstructured":"Zhang Z, Lan C, Zeng W, et al. (2020) Uncertainty-aware few-shot image classification. arXiv:2010.04525","DOI":"10.24963\/ijcai.2021\/471"},{"key":"2189_CR43","doi-asserted-by":"crossref","unstructured":"Wu Z, Li Y, Guo L, et al. (2019) Parn: position-aware relation networks for few-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision. pp 6659\u20136667","DOI":"10.1109\/ICCV.2019.00676"},{"key":"2189_CR44","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, et al. (2020) End-to-end object detection with transformers. In: Proceedings of European Conference on Computer Vision, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2189_CR45","doi-asserted-by":"crossref","unstructured":"Guan T, Wang J, Lan S, et al. (2022) M3detr: multi-representation, multi-scale, mutual-relation 3d object detection with transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 772\u2013782","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"2189_CR46","unstructured":"Liu S, Zhang L, Yang X, et al. (2021) Query2label: a simple transformer way to multi-label classification. arXiv:2107.10834"},{"key":"2189_CR47","doi-asserted-by":"crossref","unstructured":"Chen Z, Cui Q, Zhao B, et al. (2022) Sst: spatial and semantic transformers for multi-label image recognition. In: IEEE Transactions on Image Processing, pp 2570\u20132583","DOI":"10.1109\/TIP.2022.3148867"},{"key":"2189_CR48","doi-asserted-by":"crossref","unstructured":"Valanarasu J, Oza P, Hacihaliloglu I, et al. (2021) Medical transformer: gated axial-attention for medical image segmentation. In: Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, pp 36\u201346","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"2189_CR49","doi-asserted-by":"crossref","unstructured":"Petit O, Thome N, Rambour C, et al. (2021) U-net transformer: Self and cross attention for medical image segmentation. In: Proceedings of International Workshop on Machine Learning in Medical Imaging, pp 267\u2013276","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"2189_CR50","doi-asserted-by":"crossref","unstructured":"Dong B, Zhou P, Yan S, et al. (2022) Self-promoted supervision for few-shot transformer. arXiv:2203.07057.","DOI":"10.1007\/978-3-031-20044-1_19"},{"key":"2189_CR51","doi-asserted-by":"crossref","unstructured":"Liu L, Hamilton W, Long G, et al. (2021) A universal representation transformer layer for few-shot image classification. In: Proceedings of the IEEE\/CVF International Conference on Learning Representations.","DOI":"10.1109\/ICCV48922.2021.00939"},{"key":"2189_CR52","doi-asserted-by":"crossref","unstructured":"Jiang B, Zhao K, Tang J. (2022) Rgtransformer: region-graph transformer for image representation and few-shot classification. In: IEEE Signal Processing Letters, pp 792\u2013796","DOI":"10.1109\/LSP.2022.3155991"},{"key":"2189_CR53","doi-asserted-by":"crossref","unstructured":"Ravichandran A, Bhotika R, Soatto S (2019) Few-shot learning with embedded class models and shot-free meta training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 331\u2013339","DOI":"10.1109\/ICCV.2019.00042"},{"key":"2189_CR54","doi-asserted-by":"crossref","unstructured":"Qiao L, Shi Y, Li J, et al. (2019) Transductive episodic-wise adaptive metric for few-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 3603\u20133612","DOI":"10.1109\/ICCV.2019.00370"},{"key":"2189_CR55","unstructured":"Laenen S, Bertinetto L (2020) On episodes, prototypical networks, and few-shot learning. arXiv preprint arXiv:2012.09831"},{"key":"2189_CR56","doi-asserted-by":"crossref","unstructured":"Gao Z, Wu Y, Jia Y, et al. (2021) Curvature generation in curved spaces for few-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 8691\u20138700","DOI":"10.1109\/ICCV48922.2021.00857"},{"key":"2189_CR57","doi-asserted-by":"crossref","unstructured":"Kim J, Kim H, Kim G. (2020) Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning. In: ECCV, pp 599\u2013617","DOI":"10.1007\/978-3-030-58452-8_35"},{"key":"2189_CR58","unstructured":"Wang Z, Miao Z, Zhen X, et al. (2021) Learning to learn dense gaussian processes for few-shot learning. In: Neural Information Processing Systems"},{"key":"2189_CR59","unstructured":"Hu S, Moreno P, Xiao Y, et al. (2020) Empirical bayes transductive meta-learning with synthetic gradients. In: International Conference on Learning Representations"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02189-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02189-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02189-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T16:37:54Z","timestamp":1726245474000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02189-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":59,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["2189"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02189-1","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"6 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}