{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T22:53:57Z","timestamp":1752360837755,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2023,3,4]],"date-time":"2023-03-04T00:00:00Z","timestamp":1677888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,4]],"date-time":"2023-03-04T00:00:00Z","timestamp":1677888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61379109"],"award-info":[{"award-number":["61379109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s11042-023-14413-1","type":"journal-article","created":{"date-parts":[[2023,3,4]],"date-time":"2023-03-04T21:13:14Z","timestamp":1677964394000},"page":"32991-33014","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learn to aggregate global and local representations for few-shot learning"],"prefix":"10.1007","volume":"82","author":[{"given":"Mounir","family":"Abdelaziz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2528-7808","authenticated-orcid":false,"given":"Zuping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,4]]},"reference":[{"issue":"7","key":"14413_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. Multimed Tools Appl 80(7):10491\u201310508","journal-title":"Multimed Tools Appl"},{"key":"14413_CR2","doi-asserted-by":"crossref","unstructured":"Abdelaziz M, Zhang Z (2022) Multi-scale kronecker-product relation networks for few-shot learning. Multimedia Tools and Applications :1\u201320","DOI":"10.1007\/s11042-021-11735-w"},{"key":"14413_CR3","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":"14413_CR4","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. Psychol Rev 94(2):115\u2013147","journal-title":"Psychol Rev"},{"key":"14413_CR5","doi-asserted-by":"crossref","unstructured":"Cai Q, Pan Y, Yao T et al (2018) Memory matching networks for One-Shot image recognition. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4080\u20134088","DOI":"10.1109\/CVPR.2018.00429"},{"key":"14413_CR6","doi-asserted-by":"crossref","unstructured":"Chen H, Li H, Li Y et al (2020) Multi-scale adaptive task attention network for few-shot learning. ArXiv:2011.14479","DOI":"10.1109\/IJCNN52387.2021.9534467"},{"key":"14413_CR7","doi-asserted-by":"crossref","unstructured":"Chen H, Li H, Li Y et al (2021) Multi-level metric learning for few-shot image recognition. arXiv:2103.11383","DOI":"10.1007\/978-3-031-15919-0_21"},{"key":"14413_CR8","doi-asserted-by":"crossref","unstructured":"Chen Z, Fu Y, Wang YX, Ma L et al (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"},{"issue":"9","key":"14413_CR9","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 et al (2019) Multi-Level Semantic feature augmentation for One-Shot learning. IEEE Trans Image Process 28(9):4594\u20134605","journal-title":"IEEE Trans Image Process"},{"key":"14413_CR10","doi-asserted-by":"crossref","unstructured":"Chu W-H, Li Y-J, Chang J-C et al (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":"14413_CR11","unstructured":"Devlin J, Chang M-W, Lee K et al (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"},{"key":"14413_CR12","doi-asserted-by":"crossref","unstructured":"Dong C, Li W, Huo J et al (2020) Learning task-aware local representations for few-shot learning. In: IJCAI, pp 716\u2013722","DOI":"10.24963\/ijcai.2020\/100"},{"issue":"4","key":"14413_CR13","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 Trans Pattern Anal Mach Intell 28(4):594\u2013611","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14413_CR14","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-volume, vol. 70, pp 1126\u20131135"},{"key":"14413_CR15","unstructured":"Flennerhag S, Rusu AA, Pascanu R et al (2020) Meta-learning with warped gradient descent. In: ICLR 2020: eighth international conference on learning representations"},{"key":"14413_CR16","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"},{"key":"14413_CR17","doi-asserted-by":"crossref","unstructured":"Hao F, He F, Cheng J et al (2019) Collect and select: semantic alignment metric learning for few-shot learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8460\u20138469","DOI":"10.1109\/ICCV.2019.00855"},{"key":"14413_CR18","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":"14413_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (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":"14413_CR20","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 (CVPR), pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"14413_CR21","unstructured":"Khosla A, Jayadevaprakash N, Yao B et al (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":"14413_CR22","unstructured":"Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: ICLR 2015: international conference on learning representations, p 2015"},{"key":"14413_CR23","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, vol. 2"},{"key":"14413_CR24","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J et al (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":"14413_CR25","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":"14413_CR26","unstructured":"Lake BM, Salakhutdinov R, Gross J et al (2011) One shot learning of simple visual concepts. Cogn Sci 33:33"},{"key":"14413_CR27","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":"14413_CR28","doi-asserted-by":"crossref","unstructured":"Li W, Wang L, Huo J, et al. (2020) Asymmetric distribution measure for few-shot learning. arXiv:2002.00153","DOI":"10.24963\/ijcai.2020\/409"},{"key":"14413_CR29","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: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7260\u20137268","DOI":"10.1109\/CVPR.2019.00743"},{"key":"14413_CR30","unstructured":"Li Y, Li H, Chen H, et al. (2021)"},{"key":"14413_CR31","unstructured":"Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: learning to learn quickly for few-shot learning. ArXiv:1707.09835"},{"key":"14413_CR32","unstructured":"Mishra N, Rohaninejad M, Chen X et al (2017) A simple neural attentive meta-learner. arXiv:1707.03141"},{"key":"14413_CR33","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":"14413_CR34","unstructured":"Oh J, Yoo H, Kim C et al (2021) BOIL: towards representation change for few-shot learning. In: ICLR 2021: the ninth international conference on learning representations"},{"key":"14413_CR35","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":"14413_CR36","unstructured":"Ravi S, Larochelle H (2017) Optimization as a model for Few-Shot learning. In: ICLR 2017: international conference on learning representations, p 2017"},{"key":"14413_CR37","unstructured":"Ren M, Ravi S, Triantafillou E et al (2018) Meta-learning for semi-supervised few-shot classification. In: ICLR 2018: international conference on learning representations, p 2018"},{"key":"14413_CR38","unstructured":"Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum JB, et al. (2018) Meta-learning for semi-supervised few-shot classification. arXiv:1803.00676"},{"issue":"3","key":"14413_CR39","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 (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"14413_CR40","unstructured":"Santoro A, Bartunov S, Botvinick M et al (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":"14413_CR41","unstructured":"Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: International conference on learning representations"},{"key":"14413_CR42","unstructured":"Schwartz E, Karlinsky L, Feris RS et al (2019) Baby steps towards few-shot learning with multiple semantics. ArXiv:1906.01905"},{"key":"14413_CR43","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A et al (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":"14413_CR44","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":"14413_CR45","unstructured":"Steiner B, DeVito Z, Chintala S et al (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":"14413_CR46","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L et al (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":"14413_CR47","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (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":"14413_CR48","unstructured":"Tao A, Sapra K, Catanzaro B (2020) Hierarchical multi-scale attention for semantic segmentation. ArXiv:2005.10821"},{"key":"14413_CR49","doi-asserted-by":"crossref","unstructured":"Thrun S, Pratt L (1998) Learning to learn: introduction and overview. Learning to Learn :3\u201317","DOI":"10.1007\/978-1-4615-5529-2_1"},{"issue":"2","key":"14413_CR50","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. Artif Intell Rev 18(2):77\u201395","journal-title":"Artif Intell Rev"},{"key":"14413_CR51","unstructured":"Vinyals O, Blundell C, Lillicrap T et al (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":"14413_CR52","doi-asserted-by":"crossref","unstructured":"Wang YX, Girshick R, Hebert M et al (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":"14413_CR53","unstructured":"Welinder P, Branson S, Mita T et al (2010) Caltech-UCSD birds 200"},{"key":"14413_CR54","unstructured":"Xing C, Rostamzadeh N, Oreshkin B et al (2019) Adaptive cross-modal few-shot learning. In: NeurIPS 2019: Thirty-third conference on neural information processing systems, pp 4848\u20134858"},{"key":"14413_CR55","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"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14413-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14413-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14413-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T09:36:25Z","timestamp":1693474585000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14413-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,4]]},"references-count":55,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["14413"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14413-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,3,4]]},"assertion":[{"value":"23 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2023","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":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}