{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:00:18Z","timestamp":1781280018475,"version":"3.54.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11042-021-11735-w","type":"journal-article","created":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T15:03:55Z","timestamp":1642431835000},"page":"6703-6722","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Multi-scale kronecker-product relation networks for few-shot learning"],"prefix":"10.1007","volume":"81","author":[{"given":"Mounir","family":"Abdelaziz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2528-7808","authenticated-orcid":false,"given":"Zuping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,17]]},"reference":[{"issue":"7","key":"11735_CR1","doi-asserted-by":"publisher","first-page":"10491","DOI":"10.1007\/s11042-020-09875-6","volume":"80","author":"M Abdelaziz","year":"2021","unstructured":"Abdelaziz M, Zhang Z (2021) Few-shot learning with saliency maps as additional visual information. Multimedia Tools and Applications 80(7):10491\u201310508","journal-title":"Multimedia Tools and Applications"},{"key":"11735_CR2","doi-asserted-by":"crossref","unstructured":"Baik S, Hong S, Lee KM (2020) Learning to forget for meta-learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 2379\u20132387","DOI":"10.1109\/CVPR42600.2020.00245"},{"issue":"2","key":"11735_CR3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","volume":"94","author":"I Biederman","year":"1987","unstructured":"Biederman I (1987) Recognition-by-components: A theory of human image understanding. Psychological Review 94(2):115\u2013147","journal-title":"Psychological Review"},{"key":"11735_CR4","doi-asserted-by":"crossref","unstructured":"Cai Q, Pan Y, Yao T, Yan C, Mei T (2018) Memory matching networks for one-shot image recognition. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 4080\u20134088","DOI":"10.1109\/CVPR.2018.00429"},{"issue":"9","key":"11735_CR5","doi-asserted-by":"publisher","first-page":"4594","DOI":"10.1109\/TIP.2019.2910052","volume":"28","author":"Z Chen","year":"2019","unstructured":"Chen Z, Fu Y, Zhang Y, Jiang Y-G, Xue X, Sigal L (2019) Multi-level semantic feature augmentation for one-shot learning. IEEE Transactions on Image Processing 28(9):4594\u20134605","journal-title":"IEEE Transactions on Image Processing"},{"key":"11735_CR6","doi-asserted-by":"crossref","unstructured":"Chen Z, Fu Y, Wang Y-X, Ma L, Liu W, Hebert M (2019) Image deformation meta-networks for one-shot learning. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 8680\u20138689","DOI":"10.1109\/CVPR.2019.00888"},{"key":"11735_CR7","doi-asserted-by":"crossref","unstructured":"Chen H, Li H, Li Y, Chen C (2020) Multi-scale adaptive task attention network for few-shot learning. arXiv:2011.14479","DOI":"10.1109\/IJCNN52387.2021.9534467"},{"key":"11735_CR8","doi-asserted-by":"crossref","unstructured":"Chu W-H, Li Y-J, Chang J-C, Wang Y-CF (2019) Spot and learn: A maximum-entropy patch sampler for few-shot image classification. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 6251\u20136260","DOI":"10.1109\/CVPR.2019.00641"},{"key":"11735_CR9","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019: Annual conference of the north american chapter of the association for computational linguistics, pp 4171\u20134186"},{"issue":"4","key":"11735_CR10","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","volume":"28","author":"L Fei-Fei","year":"2006","unstructured":"Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(4):594\u2013611","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"11735_CR11","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th international conference on machine learning-vol 70, pp 1126\u20131135"},{"key":"11735_CR12","unstructured":"Flennerhag S, Rusu AA, Pascanu R, Visin F, Yin H, Hadsell R (2020) Meta-learning with warped gradient descent. In: ICLR 2020: Eighth international conference on learning representations"},{"key":"11735_CR13","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2018) Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4367\u20134375","DOI":"10.1109\/CVPR.2018.00459"},{"issue":"17","key":"11735_CR14","doi-asserted-by":"publisher","first-page":"11617","DOI":"10.1007\/s11042-019-08413-3","volume":"79","author":"M Han","year":"2020","unstructured":"Han M, Wang R, Yang J, Xue L, Hu M (2020) Multi-scale feature network for few-shot learning. Multimedia Tools and Applications 79(17):11617\u201311637","journal-title":"Multimedia Tools and Applications"},{"key":"11735_CR15","doi-asserted-by":"crossref","unstructured":"Hariharan B, Girshick R (2017) Low-shot visual recognition by shrinking and hallucinating features. In: 2017 IEEE International conference on computer vision (ICCV), pp 3037\u20133046","DOI":"10.1109\/ICCV.2017.328"},{"key":"11735_CR16","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11735_CR17","doi-asserted-by":"crossref","unstructured":"Huang H, Zhang J, Zhang J, Xu J, Wu Q (2020) Low-rank pairwise alignment bilinear network for few-shot fine-grained image classification. IEEE Transactions on Multimedia","DOI":"10.1109\/ICME.2019.00024"},{"key":"11735_CR18","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11735_CR19","unstructured":"Khosla A, Jayadevaprakash N, Yao B, Li FF (2011) Novel dataset for fine-grained image categorization: Stanford dogs. In: Proc. CVPR workshop on fine-grained visual categorization (FGVC) (Vol. 2, No. 1)"},{"key":"11735_CR20","unstructured":"Kingma DP, Ba JL (2015) Adam: A method for stochastic optimization. In: ICLR 2015 : International conference on learning representations 2015"},{"key":"11735_CR21","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, vol 2"},{"key":"11735_CR22","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-Fei L (2013) 3D Object representations for fine-grained categorization. In: 2013 IEEE International conference on computer vision workshops, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"6","key":"11735_CR23","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Communications of The ACM 60(6):84\u201390","journal-title":"Communications of The ACM"},{"key":"11735_CR24","unstructured":"Lake BM, Salakhutdinov R, Gross J, Tenenbaum JB (2011) One shot learning of simple visual concepts. Cogn Sci:33(33)"},{"key":"11735_CR25","doi-asserted-by":"crossref","unstructured":"Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 10657\u201310665","DOI":"10.1109\/CVPR.2019.01091"},{"key":"11735_CR26","doi-asserted-by":"crossref","unstructured":"Li W, Wang L, Xu J, Huo J, Gao Y, Luo J (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 7260\u20137268","DOI":"10.1109\/CVPR.2019.00743"},{"key":"11735_CR27","unstructured":"Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: Learning to learn quickly for few-shot learning. arXiv:1707.09835"},{"key":"11735_CR28","unstructured":"Mishra N, Rohaninejad M, Chen X, Abbeel P (2017) A simple neural attentive meta-learner. arXiv:1707.03141"},{"key":"11735_CR29","unstructured":"Munkhdalai T, Yu H (2017) Meta networks. In: ICML\u201917 Proceedings of the 34th international conference on machine learning - vol 70, pp 2554\u20132563"},{"key":"11735_CR30","unstructured":"Oh J, Yoo H, Kim C, Yun S-Y (2021) BOIL: Towards representation change for few-shot learning. In: ICLR 2021: The ninth international conference on learning representations"},{"key":"11735_CR31","unstructured":"Oreshkin B, L\u00f3pez PR, Lacoste A (2018) TADAM: Task dependent adaptive metric for improved few-shot learning. In: NIPS 2018: The 32nd annual conference on neural information processing systems, pp 721\u2013731"},{"key":"11735_CR32","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"11735_CR33","unstructured":"Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: ICLR 2017: International conference on learning representations 2017"},{"key":"11735_CR34","unstructured":"Ren M, Ravi S, Triantafillou E, Snell J, Swersky K, Tenenbaum JB, Zemel RS (2018) Meta-learning for semi-supervised few-shot classification. In: ICLR 2018: International conference on learning representations 2018"},{"issue":"3","key":"11735_CR35","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, Krause J, Satheesh S, Ma S, Bernstein M (2015) ImageNet large scale visual recognition challenge. International Journal of Computer Vision 115(3):211\u2013252","journal-title":"International Journal of Computer Vision"},{"key":"11735_CR36","unstructured":"Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) Meta-learning with memory-augmented neural networks. In: ICML\u201916 Proceedings of the 33rd international conference on international conference on machine learning - vol 48, pp 1842\u20131850"},{"key":"11735_CR37","unstructured":"Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: 6th International conference on learning representations, ICLR 2018"},{"key":"11735_CR38","unstructured":"Schwartz E, Karlinsky L, Feris RS, Giryes R, Bronstein AM (2019) Baby steps towards few-shot learning with multiple semantics. arXiv:1906.01905"},{"key":"11735_CR39","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"11735_CR40","doi-asserted-by":"crossref","unstructured":"Shen Y, Xiao T, Li H, Yi S, Wang X (2018) End-to-end deep kronecker-product matching for person re-identification. In: 2018 IEEE CVF Conference on computer vision and pattern recognition, pp 6886\u20136895","DOI":"10.1109\/CVPR.2018.00720"},{"key":"11735_CR41","doi-asserted-by":"crossref","unstructured":"Shen Y, Xiao T, Yi S, Chen D, Wang X, Li H (2020) Person re-identification with deep kronecker-product matching and group-shuffling random walk. IEEE Trans Pattern Anal Mach Intell:1\u20131","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"11735_CR42","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, pp 4077\u20134087"},{"key":"11735_CR43","unstructured":"Steiner B, DeVito Z, Chintala S, Gross S, Paszke A, Massa F, Yang, E (2019) PyTorch: An imperative style, high-performance deep learning library. In: NeurIPS 2019: Thirty-third conference on neural information processing systems, pp 8024\u20138035"},{"key":"11735_CR44","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PHS, Hospedales TM (2018) Learning to compare: Relation network for few-shot learning. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"11735_CR45","doi-asserted-by":"crossref","unstructured":"Tan, M et al (2020) EfficientDet: Scalable and efficient object detection. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"11735_CR46","unstructured":"Tao A, Sapra K, Catanzaro B (2020) Hierarchical multi-scale attention for semantic segmentation. arXiv:arXiv:2005.10821"},{"key":"11735_CR47","doi-asserted-by":"crossref","unstructured":"Thrun S, Pratt L (1998) Learning to learn: introduction and overview. Learning Learn:3\u201317","DOI":"10.1007\/978-1-4615-5529-2_1"},{"issue":"2","key":"11735_CR48","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1023\/A:1019956318069","volume":"18","author":"R Vilalta","year":"2002","unstructured":"Vilalta R, Drissi Y (2002) A perspective view and survey of meta-learning. Artificial Intelligence Review 18(2):77\u201395","journal-title":"Artificial Intelligence Review"},{"key":"11735_CR49","unstructured":"Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. In NIPS\u201916 Proceedings of the 30th international conference on neural information processing systems, pp 3637\u20133645"},{"key":"11735_CR50","doi-asserted-by":"crossref","unstructured":"Wang Y-X, Girshick R, Hebert M, Hariharan B (2018) Low-shot learning from imaginary data. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 7278\u20137286","DOI":"10.1109\/CVPR.2018.00760"},{"key":"11735_CR51","first-page":"92172","volume":"8","author":"X Wang","year":"2020","unstructured":"Wang X, Ma B, Yu Z, Li F, Cai Y (2020) Multi-scale decision network with feature fusion and weighting for few-shot learning. IEEE Access 8:92172\u201392181","journal-title":"IEEE Access"},{"key":"11735_CR52","unstructured":"Welinder P, Branson S, Mita T, Wah C, Schroff F, Belongie S, Perona P (2010) Caltech-UCSD birds 200"},{"key":"11735_CR53","doi-asserted-by":"crossref","unstructured":"Wu Z, Li Y, Guo L, Jia K (2019) Parn: Position-aware relation networks for few-shot learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6659\u20136667","DOI":"10.1109\/ICCV.2019.00676"},{"key":"11735_CR54","unstructured":"Xing C, Rostamzadeh N, Oreshkin B, Pinheiro PO (2019) Adaptive cross-modal few-shot learning. In: NeurIPS 2019: Thirty-third conference on neural information processing systems, pp 4848-4858"},{"key":"11735_CR55","unstructured":"Xue Z, Duan L, Li W, Chen L, Luo J (2020) Region comparison network for interpretable few-shot image classification. arXiv:2009.03558"},{"key":"11735_CR56","doi-asserted-by":"crossref","unstructured":"Xue Z, Xie Z, Xing Z, Duan L (2020) Relative position and map networks in few-shot learning for image classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 932\u2013933","DOI":"10.1109\/CVPRW50498.2020.00474"},{"key":"11735_CR57","doi-asserted-by":"crossref","unstructured":"Zhang H, Koniusz P (2019) Power normalizing second-order similarity network for few-shot learning. In: 2019 IEEE Winter conference on applications of computer vision (WACV), pp 1185\u20131193","DOI":"10.1109\/WACV.2019.00131"},{"key":"11735_CR58","unstructured":"Zhang H, Torr PH, Koniusz P (2020) Few-shot Learning with multi-scale self-supervision. arXiv:2001.01600"},{"key":"11735_CR59","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhang J, Koniusz P (2019) Few-shot learning via saliency-guided hallucination of samples. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 2770\u20132779","DOI":"10.1109\/CVPR.2019.00288"},{"key":"11735_CR60","doi-asserted-by":"crossref","unstructured":"Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: Proceedings of the AAAI conference on artificial intelligence, pp 13001\u201313008","DOI":"10.1609\/aaai.v34i07.7000"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11735-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11735-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11735-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T08:22:00Z","timestamp":1645604520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11735-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,17]]},"references-count":60,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["11735"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11735-w","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,17]]},"assertion":[{"value":"6 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}