{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T09:21:18Z","timestamp":1775380878803,"version":"3.50.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T00:00:00Z","timestamp":1627603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T00:00:00Z","timestamp":1627603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s11432-020-2973-7","type":"journal-article","created":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T06:03:02Z","timestamp":1627970582000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Learning to focus: cascaded feature matching network for few-shot image recognition"],"prefix":"10.1007","volume":"64","author":[{"given":"Mengting","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,30]]},"reference":[{"key":"2973_CR1","doi-asserted-by":"crossref","unstructured":"He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"2973_CR2","unstructured":"Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. In: Proceedings of Neural Information Processing Systems (NeurIPS), 2012"},{"key":"2973_CR3","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations (ICLR), 2015"},{"key":"2973_CR4","unstructured":"Wu Y H, Schuster M, Chen Z F, et al. Google\u2019s neural machine translation system: bridging the gap between human and machine translation. 2016. ArXiv:1609.08144"},{"key":"2973_CR5","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. 2014. ArXiv:1409.0473"},{"key":"2973_CR6","unstructured":"Oord A V D, Dieleman S, Zen H, et al. Wavenet: a generative model for raw audio. 2016. ArXiv:1609.03499"},{"key":"2973_CR7","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3577.001.0001","volume-title":"How Children Learn the Meanings of Words","author":"P Bloom","year":"2000","unstructured":"Bloom P. How Children Learn the Meanings of Words. Cambridge: MIT Press, 2000"},{"key":"2973_CR8","unstructured":"Vinyals O, Blundell C, Lillicrap T, et al. Matching networks for one shot learning. In: Proceedings of Neural Information Processing Systems (NeurIPS), 2016"},{"key":"2973_CR9","unstructured":"Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of International Conference on Machine Learning (ICML), 2017"},{"key":"2973_CR10","unstructured":"Snell J, Swersky K, Zemel R. Prototypical networks for few-shot learning. In: Proceedings of Neural Information Processing Systems (NeurIPS), 2017"},{"key":"2973_CR11","unstructured":"Graves A, Wayne G, Danihelka I. Neural Turing machines. 2014. ArXiv:1410.5401"},{"key":"2973_CR12","unstructured":"Santoro A, Bartunov S, Botvinick M, et al. Meta-learning with memory-augmented neural networks. In: Proceedings of International Conference on Machine Learning (ICML), 2016"},{"key":"2973_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9: 1735\u20131780","journal-title":"Neural Comput"},{"key":"2973_CR14","unstructured":"Munkhdalai T, Yu H. Meta networks. In: Proceedings of International Conference on Machine Learning (ICML), 2017"},{"key":"2973_CR15","unstructured":"Ravi S, Larochelle H. Optimization as a model for few-shot learning. In: Proceedings of International Conference on Learning Representations (ICLR), 2017"},{"key":"2973_CR16","unstructured":"Oreshkin B, L\u00f3pez P R, Lacoste A. TADAM: task dependent adaptive metric for improved few-shot learning. In: Proceedings of Neural Information Processing Systems (NIPS), 2018"},{"key":"2973_CR17","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y X, Zhang L, et al. Learning to compare: relation network for few-shot learning. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00131"},{"key":"2973_CR18","doi-asserted-by":"crossref","unstructured":"Qiao S Y, Liu C X, Shen W, et al. Few-shot image recognition by predicting parameters from activations. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00755"},{"key":"2973_CR19","doi-asserted-by":"crossref","unstructured":"Qi H, Brown M, Lowe D G. Low-shot learning with imprinted weights. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00610"},{"key":"2973_CR20","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N. Dynamic few-shot visual learning without forgetting. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00459"},{"key":"2973_CR21","unstructured":"Bertinetto L, Henriques J F, Torr P H, et al. Meta-learning with differentiable closed-form solvers. In: Proceedings of International Conference on Learning Representations (ICLR), 2019"},{"key":"2973_CR22","doi-asserted-by":"crossref","unstructured":"Wang Y X, Hebert M. Learning to learn: model regression networks for easy small sample learning. In: Proceedings of European Conference on Computer Vision (ECCV), 2016","DOI":"10.1007\/978-3-319-46466-4_37"},{"key":"2973_CR23","doi-asserted-by":"crossref","unstructured":"Liu L, Zhou T Y, Long G D, et al. Prototype propagation networks (PPN) for weakly-supervised few-shot learning on category graph. In: Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI), 2019","DOI":"10.24963\/ijcai.2019\/418"},{"key":"2973_CR24","unstructured":"Liu Y B, Lee J, Park M, et al. Learning to propagate labels: transductive propagation network for few-shot learning. In: Proceedings of International Conference on Learning Representations (ICLR), 2019"},{"key":"2973_CR25","doi-asserted-by":"crossref","unstructured":"Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of International Conference on Computer Vision (ICCV), 2017","DOI":"10.1109\/ICCV.2017.244"},{"key":"2973_CR26","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: Proceedings of Neural Information Processing Systems (NIPS), 2014"},{"key":"2973_CR27","doi-asserted-by":"crossref","unstructured":"Dixit M, Kwitt R, Niethammer M, et al. AGA: Attribute-guided augmentation. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.355"},{"key":"2973_CR28","doi-asserted-by":"crossref","unstructured":"Liu B, Wang X D, Dixit M, et al. Feature space transfer for data augmentation. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00947"},{"key":"2973_CR29","doi-asserted-by":"crossref","unstructured":"Hariharan B, Girshick R. Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of International Conference on Computer Vision (ICCV), 2017","DOI":"10.1109\/ICCV.2017.328"},{"key":"2973_CR30","unstructured":"Schwartz E, Karlinsky L, Shtok J, et al. Delta-encoder: an effective sample synthesis method for few-shot object recognition. In: Proceedings of Neural Information Processing Systems (NIPS), 2018"},{"key":"2973_CR31","doi-asserted-by":"crossref","unstructured":"Wang Y X, Girshick R, Hebert M, et al. Low-shot learning from imaginary data. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00760"},{"key":"2973_CR32","doi-asserted-by":"crossref","unstructured":"Chen M T, Fang Y X, Wang X G, et al. Diversity transfer network for few-shot learning. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), 2020","DOI":"10.1609\/aaai.v34i07.6628"},{"key":"2973_CR33","doi-asserted-by":"crossref","unstructured":"Chen Z T, Fu Y W, Wang Y X, et al. Image deformation meta-networks for one-shot learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00888"},{"key":"2973_CR34","doi-asserted-by":"crossref","unstructured":"Zhang H G, Zhang J, Koniusz P. Few-shot learning via saliency-guided hallucination of samples. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019","DOI":"10.1109\/CVPR.2019.00288"},{"key":"2973_CR35","doi-asserted-by":"crossref","unstructured":"Thewlis J, Zheng S, Torr P H, et al. Fully-trainable deep matching. In: Proceedings of British Machine Vision Conference (BMVC), 2016","DOI":"10.5244\/C.30.145"},{"key":"2973_CR36","doi-asserted-by":"crossref","unstructured":"Novotny D, Larlus D, Vedaldi A. Anchornet: a weakly supervised network to learn geometry-sensitive features for semantic matching. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.306"},{"key":"2973_CR37","doi-asserted-by":"crossref","unstructured":"Wang Q Q, Zhou X W, Daniilidis K. Multi-image semantic matching by mining consistent features. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2018","DOI":"10.1109\/CVPR.2018.00078"},{"key":"2973_CR38","unstructured":"Xu K, Ba J, Kiros R, et al. Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of International Conference on Machine Learning (ICML), 2015"},{"key":"2973_CR39","doi-asserted-by":"crossref","unstructured":"Yang Z C, He X D, Gao J F, et al. Stacked attention networks for image question answering. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2016","DOI":"10.1109\/CVPR.2016.10"},{"key":"2973_CR40","doi-asserted-by":"crossref","unstructured":"Wang P, Liu L Q, Shen C H, et al. Multi-attention network for one shot learning. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2017","DOI":"10.1109\/CVPR.2017.658"},{"key":"2973_CR41","doi-asserted-by":"crossref","unstructured":"Chu W H, Wang Y C F. Learning semantics-guided visual attention for few-shot image classification. In: Proceedings of International Conference on Image Processing (ICIP), 2018","DOI":"10.1109\/ICIP.2018.8451350"},{"key":"2973_CR42","doi-asserted-by":"crossref","unstructured":"Cheng J P, Dong L, Lapata M. Long short-term memory-networks for machine reading. In: Proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2016","DOI":"10.18653\/v1\/D16-1053"},{"key":"2973_CR43","doi-asserted-by":"crossref","unstructured":"Parikh A P, T\u00e4ckstr\u00f6m O, Das D, et al. A decomposable attention model for natural language inference. In: Proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2016","DOI":"10.18653\/v1\/D16-1244"},{"key":"2973_CR44","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Neural Information Processing Systems (NeurIPS), 2017"},{"key":"2973_CR45","unstructured":"Parmar N, Vaswani A, Uszkoreit J, et al. Image transformer. 2018. ArXiv:1802.05751"},{"key":"2973_CR46","doi-asserted-by":"crossref","unstructured":"Wang X L, Girshick R, Gupta A, et al. Non-local neural networks. 2017. ArXiv:1711.07971","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2973_CR47","unstructured":"Zhang H, Goodfellow I, Metaxas D, et al. Self-attention generative adversarial networks. 2018. ArXiv:1805.08318"},{"key":"2973_CR48","doi-asserted-by":"crossref","unstructured":"Yan S P, Zhang S Y, He X M, et al. A dual attention network with semantic embedding for few-shot learning. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), 2019","DOI":"10.1609\/aaai.v33i01.33019079"},{"key":"2973_CR49","unstructured":"Zhang X T, Sung F, Qiang Y T, et al. Deep comparison: relation columns for few-shot learning. 2018. ArXiv:1811.07100"},{"key":"2973_CR50","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"B M Lake","year":"2015","unstructured":"Lake B M, Salakhutdinov R, Tenenbaum J B. Human-level concept learning through probabilistic program induction. Science, 2015, 350: 1332\u20131338","journal-title":"Science"},{"key":"2973_CR51","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis, 2015, 115: 211\u2013252","journal-title":"Int J Comput Vis"},{"key":"2973_CR52","doi-asserted-by":"crossref","unstructured":"Lin T Y, Maire M, Belongie S, et al. Microsoft coco: common objects in context. In: Proceedings of European Conference on Computer Vision (ECCV), 2014","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2973_CR53","unstructured":"Paszke A, Gross S, Chintala S, et al. Automatic differentiation in PyTorch. In: Proceedings of Neural Information Processing Systems (NIPS) Workshop, 2017"},{"key":"2973_CR54","unstructured":"Kinga D, Adam J B. A method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (ICLR), 2015"},{"key":"2973_CR55","unstructured":"Edwards H, Storkey A. Towards a neural statistician. In: Proceedings of International Conference on Learning Representations (ICLR), 2017"},{"key":"2973_CR56","unstructured":"Kaiser \u0141, Nachum O, Roy A, et al. Learning to remember rare events. In: Proceedings of International Conference on Learning Representations (ICLR), 2017"},{"key":"2973_CR57","doi-asserted-by":"crossref","unstructured":"Huang Z L, Wang X G, Huang L C, et al. CCNET: criss-cross attention for semantic segmentation. In: Proceedings of International Conference on Computer Vision (ICCV), 2019. 603\u2013612","DOI":"10.1109\/ICCV.2019.00069"},{"key":"2973_CR58","doi-asserted-by":"crossref","unstructured":"Kang B Y, Liu Z, Wang X, et al. Few-shot object detection via feature reweighting. In: Proceedings of International Conference on Computer Vision (ICCV), 2019. 8420\u20138429","DOI":"10.1109\/ICCV.2019.00851"},{"key":"2973_CR59","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1109\/TPAMI.2018.2876304","volume":"42","author":"P Tang","year":"2020","unstructured":"Tang P, Wang X G, Bai S, et al. PCL: proposal cluster learning for weakly supervised object detection. IEEE Trans Pattern Anal Mach Intell, 2020, 42: 176\u2013191","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-020-2973-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-020-2973-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-020-2973-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T20:16:28Z","timestamp":1666296988000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-020-2973-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,30]]},"references-count":59,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["2973"],"URL":"https:\/\/doi.org\/10.1007\/s11432-020-2973-7","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,30]]},"assertion":[{"value":"27 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"192105"}}