{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T06:23:30Z","timestamp":1743575010236,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T00:00:00Z","timestamp":1606176000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T00:00:00Z","timestamp":1606176000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s11042-020-09875-6","type":"journal-article","created":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T14:07:59Z","timestamp":1606226879000},"page":"10491-10508","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Few-shot learning with saliency maps as additional visual information"],"prefix":"10.1007","volume":"80","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":[[2020,11,24]]},"reference":[{"issue":"2","key":"9875_CR1","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":"9875_CR2","unstructured":"Boureau Y, Ponce J, Lecun Y (2010) A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th international conference on machine learning, pp 111\u2013118"},{"key":"9875_CR3","doi-asserted-by":"crossref","unstructured":"Carreira J, Caseiro R, Batista J, Sminchisescu C (2012) Semantic segmentation with second-order pooling. In: ECCV\u201912 proceedings of the 12th european conference on computer vision - Volume Part VII, pp 430\u2013443","DOI":"10.1007\/978-3-642-33786-4_32"},{"key":"9875_CR4","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"},{"issue":"9","key":"9875_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 Trans Image Process 28(9):4594\u20134605","journal-title":"IEEE Trans Image Process"},{"key":"9875_CR6","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"},{"key":"9875_CR7","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":"9875_CR8","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 Intel 28(4):594\u2013611","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"key":"9875_CR9","first-page":"1126","volume":"70","author":"C Finn","year":"2017","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning 70:1126\u20131135","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"issue":"2","key":"9875_CR10","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/MNET.001.1900260","volume":"34","author":"Z Gao","year":"2020","unstructured":"Gao Z, Zhang H, Dong S, Sun S, Wang X, Yang G, de Albuquerque VHC (2020) Salient object detection in the distributed cloud-edge intelligent network. IEEE Netw 34(2):216\u2013224","journal-title":"IEEE Netw"},{"key":"9875_CR11","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":"9875_CR12","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":"9875_CR13","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":"9875_CR14","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":"9875_CR15","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of The 32nd international conference on machine learning, pp 448\u2013456"},{"key":"9875_CR16","doi-asserted-by":"crossref","unstructured":"Jegou H, Douze M, Schmid C (2009) On the burstiness of visual elements. In: 2009 IEEE conference on computer vision and pattern recognition, pp 1169\u20131176","DOI":"10.1109\/CVPR.2009.5206609"},{"key":"9875_CR17","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":"9875_CR18","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop, vol 2"},{"key":"9875_CR19","doi-asserted-by":"crossref","unstructured":"Koniusz P, Tas Y, Zhang H, Harandi MT, Porikli F, Zhang R (2018) Museum exhibit identification challenge for the supervised domain adaptation and beyond. In: Proceedings of the European conference on computer vision (ECCV), pp 815\u2013833","DOI":"10.1007\/978-3-030-01270-0_48"},{"key":"9875_CR20","unstructured":"Koniusz P, Yan F, Gosselin P-H, Mikolajczyk K (2013) Higher-order Occurrence Pooling on Mid- and Low-level Features: Visual Concept Detection"},{"issue":"2","key":"9875_CR21","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1109\/TPAMI.2016.2545667","volume":"39","author":"P Koniusz","year":"2017","unstructured":"Koniusz P, Yan F, Gosselin P-H, Mikolajczyk K (2017) Higher-order occurrence pooling for bags-of-words: visual concept detection. IEEE Trans Pattern Anal Mach Intel 39(2):313\u2013326","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"issue":"5","key":"9875_CR22","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1016\/j.cviu.2012.10.010","volume":"117","author":"P Koniusz","year":"2013","unstructured":"Koniusz P, Yan F, Mikolajczyk K (2013) Comparison of mid-level feature coding approaches and pooling strategies in visual concept detection. Comput Vis Image Underst 117(5):479\u2013492","journal-title":"Comput Vis Image Underst"},{"key":"9875_CR23","doi-asserted-by":"crossref","unstructured":"Koniusz P, Zhang H, Porikli F (2018) A deeper look at power normalizations. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 5774\u20135783","DOI":"10.1109\/CVPR.2018.00605"},{"issue":"6","key":"9875_CR24","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":"9875_CR25","unstructured":"Lake BM, Salakhutdinov R, Gross J, Tenenbaum JB (2011) One shot learning of simple visual concepts. Cogn Sci, 33(33)"},{"key":"9875_CR26","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":"9875_CR27","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"},{"issue":"2","key":"9875_CR28","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1109\/TPAMI.2010.70","volume":"33","author":"T Liu","year":"2011","unstructured":"Liu T, Yuan Z, Sun J, Wang J, Zheng N, Tang X, Shum H-Y (2011) Learning to detect a salient object. IEEE Trans Pattern Anal Mach Intel 33(2):353\u2013367","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"key":"9875_CR29","unstructured":"Munkhdalai T, Yu H (2017)"},{"key":"9875_CR30","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: ICML"},{"key":"9875_CR31","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.imavis.2016.07.007","volume":"54","author":"K Oh","year":"2016","unstructured":"Oh K, Lee M, Kim G, Kim S (2016) Detection of multiple salient objects through the integration of estimated foreground clues. Image Vis Comput 54:31\u201344","journal-title":"Image Vis Comput"},{"key":"9875_CR32","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"},{"issue":"1","key":"9875_CR33","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TSMC.2016.2564922","volume":"47","author":"Q Peng","year":"2016","unstructured":"Peng Q, Cheung YM, You X, Tang YY (2016) A hybrid of local and global saliencies for detecting image salient region and appearance. IEEE Transactions on Systems, Man, and Cybernetics: Systems 47(1):86\u201397","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"9875_CR34","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":"9875_CR35","doi-asserted-by":"crossref","unstructured":"Qin X, Zhang Z, Huang C, Gao C, Dehghan M, Jagersand M (2019) BASNEt: boundary-aware salient object detection. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7479\u20137489","DOI":"10.1109\/CVPR.2019.00766"},{"key":"9875_CR36","unstructured":"Ravi S, Larochelle H (2017) Optimization as a model for Few-Shot learning. In: ICLR 2017: International conference on learning representations, 2017"},{"key":"9875_CR37","doi-asserted-by":"crossref","unstructured":"Romero A, Gouiff\u00e8s M, Lacassagne L (2013) Enhanced local binary covariance matrices (ELBCM) for texture analysis and object tracking. In: Proceedings of the 6th international conference on computer vision \/ computer graphics collaboration techniques and applications, pp 10","DOI":"10.1145\/2466715.2466733"},{"issue":"3","key":"9875_CR38","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. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"9875_CR39","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":"9875_CR40","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":"9875_CR41","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":"9875_CR42","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":"9875_CR43","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":"9875_CR44","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":"9875_CR45","unstructured":"Tao A, Sapra K, Catanzaro B (2020) Hierarchical Multi-Scale attention for semantic segmentation. arXiv:2005.10821"},{"key":"9875_CR46","unstructured":"Touvron H, Vedaldi A, Douze M, J\u00e9gou H (2020) Fixing the train-test resolution discrepancy: FixEfficientNet. arXiv:2003.08237"},{"key":"9875_CR47","doi-asserted-by":"crossref","unstructured":"Tuzel O, Porikli F, Meer P (2006) Region covariance: a fast descriptor for detection and classification. Lecture Notes in Computer Science, pp 589\u2013600","DOI":"10.1007\/11744047_45"},{"key":"9875_CR48","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":"9875_CR49","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"},{"key":"9875_CR50","doi-asserted-by":"crossref","unstructured":"Wang L, Lu H, Wang Y, Feng M, Wang D, Yin B, Ruan X (2017) Learning to detect salient objects with Image-Level supervision. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 3796\u20133805","DOI":"10.1109\/CVPR.2017.404"},{"key":"9875_CR51","doi-asserted-by":"crossref","unstructured":"Wang L, Wang L, Lu H, Zhang P, Ruan X (2016) Saliency detection with recurrent fully convolutional networks. In: European conference on computer vision, pp 825\u2013841","DOI":"10.1007\/978-3-319-46493-0_50"},{"key":"9875_CR52","unstructured":"Welinder P, Branson S, Mita T, Wah C, Schroff F, Belongie S, Perona P (2010) Caltech-UCSD birds 200"},{"key":"9875_CR53","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\u20134858"},{"issue":"9","key":"9875_CR54","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1007\/s00371-019-01774-8","volume":"36","author":"S Zhang","year":"2020","unstructured":"Zhang S, He F (2020) DRCDN: Learning deep residual convolutional dehazing networks. Vis Comput 36(9):1797\u20131808","journal-title":"Vis Comput"},{"key":"9875_CR55","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":"9875_CR56","doi-asserted-by":"crossref","unstructured":"Zhang J, Zhang T, Daf Y, Harandi M, Hartley R (2018) Deep unsupervised saliency detection: a multiple noisy labeling perspective. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 9029\u20139038","DOI":"10.1109\/CVPR.2018.00941"},{"key":"9875_CR57","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":"9875_CR58","doi-asserted-by":"crossref","unstructured":"Zhu W, Liang S, Wei Y, Sun J (2014) Saliency optimization from robust background detection. In: CVPR \u201914 Proceedings of the 2014 IEEE conference on computer vision and pattern recognition, pp 2814\u20132821","DOI":"10.1109\/CVPR.2014.360"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09875-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-020-09875-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09875-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T00:07:11Z","timestamp":1616717231000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-020-09875-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,24]]},"references-count":58,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["9875"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09875-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,11,24]]},"assertion":[{"value":"17 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"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"}}]}}