{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:16:18Z","timestamp":1776399378156,"version":"3.51.2"},"reference-count":100,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1007\/s00521-019-04296-5","type":"journal-article","created":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T15:02:55Z","timestamp":1562166175000},"page":"879-898","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":153,"title":["Interpretation of intelligence in CNN-pooling processes: a methodological survey"],"prefix":"10.1007","volume":"32","author":[{"given":"Nadeem","family":"Akhtar","sequence":"first","affiliation":[]},{"given":"U.","family":"Ragavendran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,3]]},"reference":[{"key":"4296_CR1","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-642-15825-4_10","volume-title":"Artificial Neural Networks \u2013 ICANN 2010","author":"Dominik Scherer","year":"2010","unstructured":"Scherer D, Muller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition, In: Proceedings of the international conference on artificial neural networks, pp 92\u2013101. \nhttps:\/\/doi.org\/10.1007\/978-3-642-15825-4_10"},{"key":"4296_CR2","doi-asserted-by":"publisher","unstructured":"Zhong Z, Jin L, Feng Z (2015) Multi-font printed Chinese character recognition using multi-pooling convolutional neural network. In: Proceedings of 13th international conference on document analysis and recognition, pp 96-100. \nhttps:\/\/doi.org\/10.1109\/ICDAR.2015.7333733","DOI":"10.1109\/ICDAR.2015.7333733"},{"key":"4296_CR3","unstructured":"Springenberg JT, Dosovitskiy A, Brox T (2015) Martin riedmiller, striving for simplicity the all convolutional net. \narXiv:1412.6806v3"},{"key":"4296_CR4","doi-asserted-by":"publisher","unstructured":"Chen J, Hua Z, Wang J, Cheng S (2017) A convolutional neural network with dynamic correlation pooling. In: Proceedings of international conference on computational intelligence and security, pp 496-499. \nhttps:\/\/doi.org\/10.1109\/CIS.2017.00115","DOI":"10.1109\/CIS.2017.00115"},{"key":"4296_CR5","unstructured":"Karpathy A (2017) Stanford University CS231n: convolutional neural networks for visual recognition. \nhttp:\/\/cs231n.stanford.edu\/syllabus.html\n\n. Accessed 28 Nov 2018"},{"key":"4296_CR6","doi-asserted-by":"publisher","first-page":"3587","DOI":"10.3390\/s18103587","volume":"18","author":"C Li","year":"2018","unstructured":"Li C, Yang SX, Yang Y, Gao H, Zhao J, Qu X, Wang Y, Yao D, Gao J (2018) Hyperspectral remote sensing image classification based on maximum overlap pooling convolutional neural network. Sensors 18:3587. \nhttps:\/\/doi.org\/10.3390\/s18103587","journal-title":"Sensors"},{"key":"4296_CR7","doi-asserted-by":"publisher","DOI":"10.1145\/3065386","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. \nhttps:\/\/doi.org\/10.1145\/3065386","journal-title":"Adv Neural Inf Process Syst"},{"issue":"9","key":"4296_CR8","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Int 37(9):1904\u20131916. \nhttps:\/\/doi.org\/10.1109\/TPAMI.2015.2389824","journal-title":"IEEE Trans Pattern Anal Mach Int"},{"key":"4296_CR9","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/978-3-319-11740-9_34","volume-title":"Rough Sets and Knowledge Technology","author":"Dingjun Yu","year":"2014","unstructured":"Yu D, Wang H, Chen P, Wei Z (2014) Mixed pooling for convolutional neural networks. In: Proceedings of the 9th international conference on rough sets and knowledge technology, pp 364\u2013375. \nhttps:\/\/doi.org\/10.1007\/978-3-319-11740-9_34"},{"key":"4296_CR10","doi-asserted-by":"crossref","unstructured":"Wu H, Gu X (2015) Max-pooling dropout for regularization of convolutional neural networks. \narXiv:1512.01400v1","DOI":"10.1016\/j.neunet.2015.07.007"},{"key":"4296_CR11","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/978-3-319-46493-0_23","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Wu Shi","year":"2016","unstructured":"Shi W, Loy CC, Tang X (2016) Deep specialized network for illuminant estimation. In: European conference on computer vision, pp 371\u2013387. \nhttps:\/\/doi.org\/10.1007\/978-3-319-46493-0_23"},{"key":"4296_CR12","doi-asserted-by":"publisher","unstructured":"Nagi J, Ducatelle F, Di Caro GA, Ciresan D, Meier U, Giusti A, Nagi F, Schmidhuber J, Gambardella LM (2011) Max-pooling convolutional neural networks for vision-based hand gesture recognition. Proceedings of the IEEE international conference on signal and image processing applications, pp 342\u2013347. \nhttps:\/\/doi.org\/10.1109\/ICSIPA.2011.6144164","DOI":"10.1109\/ICSIPA.2011.6144164"},{"key":"4296_CR13","unstructured":"Graham B (2015) Fractional max-pooling. \narXiv:1412.6071v4"},{"key":"4296_CR14","doi-asserted-by":"publisher","unstructured":"Ranzato MA, Huang FJ, Boureau Y, LeCun Y (2007) Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: Proceedings. computer vision and pattern recognition. \nhttps:\/\/doi.org\/10.1109\/CVPR.2007.383157","DOI":"10.1109\/CVPR.2007.383157"},{"key":"4296_CR15","unstructured":"Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: Proceedings of the neural information processing systems"},{"key":"4296_CR16","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/CVPR.2004.1315150","volume":"2","author":"Y LeCun","year":"2004","unstructured":"LeCun Y, Huang FJ, Bottou L (2004) Learning methods for generic object recognition with invariance to pose and lighting. Proc IEEE Conf Comput Vis Pattern Recognit 2:97\u2013104. \nhttps:\/\/doi.org\/10.1109\/CVPR.2004.1315150","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"4296_CR17","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":"4296_CR18","doi-asserted-by":"publisher","unstructured":"Lee H, Grosse R, Ranganath R, Ng AY (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the international conference on learning representations, pp 609\u2013616. \nhttps:\/\/doi.org\/10.1145\/1553374.1553453","DOI":"10.1145\/1553374.1553453"},{"issue":"11","key":"4296_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. \nhttps:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"issue":"4","key":"4296_CR20","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. \nhttps:\/\/doi.org\/10.1109\/TPAMI.2006.79","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4296_CR21","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.5591\/978-1-57735-516-8\/IJCAI11-210","volume":"1","author":"DC Ciresan","year":"2011","unstructured":"Ciresan DC, Meier U, Masci J, Maria Gambardella L, Schmidhuber J (2011) Flexible, high performance convolutional neural networks for image classification. Proc Int Joint Conf Artif Intell 1:1237\u20131242. \nhttps:\/\/doi.org\/10.5591\/978-1-57735-516-8\/IJCAI11-210","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"4296_CR22","unstructured":"Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. arXiv: 1301.3557v1"},{"key":"4296_CR23","doi-asserted-by":"publisher","unstructured":"Sainath TN, Kingsbury B, Mohamed A, Dahl GE, Saon G, Soltau H, Beran T, Aravkin Aleksandr Y, Ramabhadran B (2013) Improvements to deep convolutional neural networks for LVCSR. In: 2013 IEEE workshop on automatic speech recognition and understanding, pp 315\u2013320. \nhttps:\/\/doi.org\/10.1109\/ASRU.2013.6707749","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"4296_CR24","doi-asserted-by":"publisher","unstructured":"Jarrett K, Kavukcuoglu K, LeCun Y (2009) What is the best multi-stage architecture for object recognition?. In: Proceedings of the IEEE international conference on computer vision, pp 2146\u20132153. \nhttps:\/\/doi.org\/10.1109\/ICCV.2009.5459469","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"4296_CR25","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1016\/j.ins.2017.10.042","volume":"430\u2013431","author":"Y Long","year":"2018","unstructured":"Long Y, Zhu F, Shao L, Han J (2018) Face recognition with a small occluded training set using spatial and statistical pooling. Inf Sci 430\u2013431:634\u2013644. \nhttps:\/\/doi.org\/10.1016\/j.ins.2017.10.042","journal-title":"Inf Sci"},{"key":"4296_CR26","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1177\/1550147717748899","volume":"13","author":"F Wang","year":"2017","unstructured":"Wang F, Huang S, Shi L, Fan W (2017) The application of series multi-pooling convolutional neural networks for medical image segmentation. Int J Distrib Sensor Netw 13:12. \nhttps:\/\/doi.org\/10.1177\/1550147717748899","journal-title":"Int J Distrib Sensor Netw"},{"key":"4296_CR27","unstructured":"Eom H, Choi H (2018) Alpha-pooling for convolutional neural networks. \narXiv:1811.03436v1"},{"key":"4296_CR28","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv: 1312.4400v3"},{"key":"4296_CR29","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2018.07.079","volume":"321","author":"B Zhang","year":"2018","unstructured":"Zhang B, Zhao Q, Feng W, Lyu S (2018) AlphaMEX: a smarter global pooling method for convolutional neural networks. Neurocomputing 321:36\u201348. \nhttps:\/\/doi.org\/10.1016\/j.neucom.2018.07.079","journal-title":"Neurocomputing"},{"key":"4296_CR30","doi-asserted-by":"crossref","unstructured":"Saeedan F, Weber N, Goesele M, Roth S (2018) Detail-preserving pooling in deep networks. \narXiv:1804.04076v1","DOI":"10.1109\/CVPR.2018.00949"},{"issue":"8","key":"4296_CR31","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.neucom.2016.10.049","volume":"24","author":"M Sun","year":"2017","unstructured":"Sun M, Song Z, Jiang X, Pan J, Pang Y (2017) Learning pooling for convolutional neural network. Neurocomputing 24(8):96\u2013104. \nhttps:\/\/doi.org\/10.1016\/j.neucom.2016.10.049","journal-title":"Neurocomputing"},{"key":"4296_CR32","doi-asserted-by":"publisher","unstructured":"Grauman K, Darrell T (2005) The pyramid match kernel: discriminative classification with sets of image features. In: Proceedings of the IEEE international conference on computer vision, pp 1458\u20131465. \nhttps:\/\/doi.org\/10.1109\/ICCV.2005.239","DOI":"10.1109\/ICCV.2005.239"},{"key":"4296_CR33","doi-asserted-by":"publisher","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 2169\u20132178. \nhttps:\/\/doi.org\/10.1109\/CVPR.2006.68","DOI":"10.1109\/CVPR.2006.68"},{"key":"4296_CR34","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1109\/ICIP.2018.8451361","volume":"1","author":"A Jose","year":"2018","unstructured":"Jose A, Lopez RD, Heisterklaus I, Wien M (2018) Pyramid pooling of convolutional feature maps for image retrieval. Proc Int Conf Image Process 1:480\u2013484. \nhttps:\/\/doi.org\/10.1109\/ICIP.2018.8451361","journal-title":"Proc Int Conf Image Process"},{"issue":"4","key":"4296_CR35","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848. \nhttps:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4296_CR36","doi-asserted-by":"crossref","unstructured":"Laptev D, Savinov N, Buhmann JM, Pollefeys M (2016) TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. arXiv: 1604.06318","DOI":"10.1109\/CVPR.2016.38"},{"key":"4296_CR37","doi-asserted-by":"publisher","unstructured":"Wu J, Yu Y, Huang C, Yu K (2015) Deep multiple instance learning for image classification and auto-annotation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp 3460\u20133469. \nhttps:\/\/doi.org\/10.1109\/CVPR.2015.7298968","DOI":"10.1109\/CVPR.2015.7298968"},{"key":"4296_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. \narXiv:1409.4842v1","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4296_CR39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc Int Conf Comput Vis Pattern Recognit. \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.90","journal-title":"Proc Int Conf Comput Vis Pattern Recognit"},{"key":"4296_CR40","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1109\/CVPR.2017.325","volume":"1","author":"Y Cui","year":"2017","unstructured":"Cui Y, Zhou F, Wang J, Liu X, Lin Y, Belongie S (2017) Kernel pooling for convolutional neural networks. Int Conf Comput Vis Pattern Recognit 1:3049\u20133058. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.325","journal-title":"Int Conf Comput Vis Pattern Recognit"},{"key":"4296_CR41","unstructured":"Shahriari A, Porikli F (2017) Multipartite pooling for deep convolutional neural networks. \narXiv:1710.07435v1"},{"key":"4296_CR42","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. Master\u2019s Dissertation, University of Toronto, Canada"},{"issue":"21","key":"4296_CR43","doi-asserted-by":"publisher","first-page":"22095","DOI":"10.1007\/s11042-017-4840-5","volume":"76","author":"ST Hang","year":"2017","unstructured":"Hang ST, Aono M (2017) Bi-linearly weighted fractional max pooling: an extension to conventional max pooling for deep convolutional neural network. Int J Multimed Too Appl 76(21):22095\u201322117. \nhttps:\/\/doi.org\/10.1007\/s11042-017-4840-5","journal-title":"Int J Multimed Too Appl"},{"key":"4296_CR44","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46976-8_1","volume":"10008","author":"X-H Han","year":"2016","unstructured":"Han X-H, Lei J, Chen Y-W (2016) HEp-2 cell classification using K-support spatial pooling in deep CNNs. LNCS 10008:3\u201311. \nhttps:\/\/doi.org\/10.1007\/978-3-319-46976-8_1","journal-title":"LNCS"},{"key":"4296_CR45","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/8196906","author":"Q Zhao","year":"2018","unstructured":"Zhao Q, Lyu S, Zhang B, Feng W (2018) Multiactivation pooling method in convolutional neural networks for image recognition. Wirel Commun Mob Comput. \nhttps:\/\/doi.org\/10.1155\/2018\/8196906","journal-title":"Wirel Commun Mob Comput"},{"key":"4296_CR46","doi-asserted-by":"publisher","first-page":"45","DOI":"10.3390\/info8020045","volume":"8","author":"J Zhang","year":"2017","unstructured":"Zhang J, Huang Q, Wu H, Liu Y (2017) A shallow network with combined pooling for fast traffic sign recognition. Information 8:45\u201358. \nhttps:\/\/doi.org\/10.3390\/info8020045","journal-title":"Information"},{"key":"4296_CR47","doi-asserted-by":"publisher","first-page":"934","DOI":"10.3390\/rs10060934","volume":"10","author":"K Qi","year":"2018","unstructured":"Qi K, Guan Q, Yang C, Peng F, Shen S, Huayi W (2018) Concentric circle pooling in deep convolutional networks for remote sensing scene classification. Remote Sens 10:934. \nhttps:\/\/doi.org\/10.3390\/rs10060934","journal-title":"Remote Sens"},{"key":"4296_CR48","series-title":"Communications in computer and information science","volume-title":"Fuzzy information processing. NAFIPS 2018","author":"CA Dias","year":"2018","unstructured":"Dias CA et al (2018) Using the choquet integral in the pooling layer in deep learning networks. In: Barreto G, Coelho R (eds) Fuzzy information processing. NAFIPS 2018. Communications in computer and information science, vol 831. Springer, Cham"},{"key":"4296_CR49","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. \narXiv:1403.1840v3","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"4296_CR50","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.1109\/ICIP.2016.7532802","volume":"1","author":"T Zhi","year":"2016","unstructured":"Zhi T, Duan L-Y, Wang Y, Huang T (2016) Two-stage pooling of deep convolutional features for image retrieval. Proc Int Conf Image Process 1:2465\u20132469. \nhttps:\/\/doi.org\/10.1109\/ICIP.2016.7532802","journal-title":"Proc Int Conf Image Process"},{"key":"4296_CR51","unstructured":"Gao F, Lou Y, Bai Y, Wang S, Huang T, Duan L-Y (2017) Improving object detection with region similarity learning. \narXiv:1703.00234v1"},{"key":"4296_CR52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854","author":"W Ouyang","year":"2015","unstructured":"Ouyang W, Wang X, Zeng X, Qiu S, Luo P, Tian Y, Li H, Yang S, Wang Z, Loy C-C, Tang X (2015) DeepID-Net: deformable deep convolutional neural networks for object detection. Proc Comput Vis Pattern Recognit. \nhttps:\/\/doi.org\/10.1109\/CVPR.2015.7298854","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"4296_CR53","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1109\/CVPR.2016.234","volume":"1","author":"F Yang","year":"2016","unstructured":"Yang F, Choi W, Lin Y (2016) Exploit all the layers: fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers. Int Conf Comput Vis and Pattern Recognit 1:2129\u20132137. \nhttps:\/\/doi.org\/10.1109\/CVPR.2016.234","journal-title":"Int Conf Comput Vis and Pattern Recognit"},{"key":"4296_CR54","unstructured":"Sadigh S, Sen P (2018) Improving the resolution of cnn feature maps efficiently with multisampling. \narXiv:1805.10766v1"},{"key":"4296_CR55","unstructured":"Takeki A, Ikami D, Irie G, Aizawa K (2018) Parallel grid pooling for data augmentation. \narXiv:1803.11370v1"},{"issue":"2","key":"4296_CR56","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1080\/09548980701418942","volume":"18","author":"A Hyvarinen","year":"2007","unstructured":"Hyvarinen A, Koster U (2007) Complex cell pooling and the statistics of natural images. Netw Comput Neural Syst 18(2):81\u2013100. \nhttps:\/\/doi.org\/10.1080\/09548980701418942","journal-title":"Netw Comput Neural Syst"},{"key":"4296_CR57","unstructured":"Estrach JB, Szlam A, Lecun Y (204) Signal recovery from pooling representations. In: Proceedings of the international conference on machine learning , pp 307\u2013315. \narXiv:1311.4025v3"},{"key":"4296_CR58","unstructured":"Sermanet P, Chintala S, LeCun Y (2012) Convolutional neural networks applied to house numbers digit classification. In: Proceedings of the 21st international conference on pattern recognition, pp 3288\u20133291"},{"issue":"2","key":"4296_CR59","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1162\/neco.2009.10-08-881","volume":"22","author":"SC Turaga","year":"2010","unstructured":"Turaga SC, Murray JF, Jain V, Roth F, Helmstaedter M, Briggman K, Briggman W, Denk H Sebastian, Seung HS (2010) Convolutional networks can learn to generate affinity graphs for image segmentation. Neural Comput 22(2):511\u2013538. \nhttps:\/\/doi.org\/10.1162\/neco.2009.10-08-881","journal-title":"Neural Comput"},{"key":"4296_CR60","unstructured":"Wan L, Zeiler M, Zhang S, LeCun Y, Fergus R (2013) Regularization of neural networks using dropconnect. In: Proceedings of the 30th international conference on machine learning, vol 28(3), pp 1058\u20131066"},{"key":"4296_CR61","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv: 1207.0580"},{"key":"4296_CR62","doi-asserted-by":"publisher","unstructured":"Fei J, Fang H, Yin Q, Yang C, Wang D (2018) Restricted stochastic pooling for convolutional neural network. In: Proceedings of the 10th international conference on internet multimedia computing and service, Article No. 24. \nhttps:\/\/doi.org\/10.1145\/3240876.3240919","DOI":"10.1145\/3240876.3240919"},{"key":"4296_CR63","doi-asserted-by":"crossref","unstructured":"Zhai S, Wu H, Kumar A, Cheng Y, Lu Y, Zhang Z, Feris R (2017) S3Pool: pooling with stochastic spatial sampling.\narXiv:1611.05138v1","DOI":"10.1109\/CVPR.2017.426"},{"key":"4296_CR64","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.neunet.2018.05.015","volume":"105","author":"Z Song","year":"2018","unstructured":"Song Z, Liu Y, Song R, Chen Z, Yang J, Zhang C, Jiang Q (2018) A sparsity-based stochastic pooling mechanism for deep convolutional. Neural Netw 105:340\u2013345. \nhttps:\/\/doi.org\/10.1016\/j.neunet.2018.05.015","journal-title":"Neural Netw"},{"key":"4296_CR65","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.neunet.2016.07.003","volume":"83","author":"Z Shi","year":"2016","unstructured":"Shi Z, Ye Y, Wu Y (2016) Rank-based pooling for deep convolutional neural networks. Neural Netw 83:21\u201331. \nhttps:\/\/doi.org\/10.1016\/j.neunet.2016.07.003","journal-title":"Neural Netw"},{"key":"4296_CR66","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1007\/978-3-319-46672-9_51","volume-title":"Neural Information Processing","author":"Zhiqiang Tong","year":"2016","unstructured":"Tong Z, Aihara K, Tanaka G (2016) A hybrid pooling method for convolutional neural networks, ICONIP 2016, Part II (LNCS), vol 9948pp. 454\u2013461. \nhttps:\/\/doi.org\/10.1007\/978-3-319-46672-9_51"},{"key":"4296_CR67","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.ijleo.2017.07.045","volume":"145","author":"Y Zhang","year":"2017","unstructured":"Zhang Y, Shi B (2017) Improving pooling method for regularization of convolutional networks based on the failure probability density. Optik 145:258\u2013265. \nhttps:\/\/doi.org\/10.1016\/j.ijleo.2017.07.045","journal-title":"Optik"},{"key":"4296_CR68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.18","author":"S Bulo","year":"2014","unstructured":"Bulo S, Kontschieder P (2014) Neural decision forests for semantic image labelling. Proc IEEE Conf Comput Vis Pattern Recognit. \nhttps:\/\/doi.org\/10.1109\/CVPR.2014.18","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"4296_CR69","unstructured":"Lee C-Y, Gallagher PW, Tu Z (2015) Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree. \narXiv:1509.08985"},{"key":"4296_CR70","unstructured":"Kumar A (2018) Ordinal pooling networks: for preserving information over shrinking feature maps. \narXiv:1804.02702"},{"key":"4296_CR71","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-319-46493-0_42","volume":"9908","author":"A Kolesnikov","year":"2016","unstructured":"Kolesnikov A, Lampert CH (2016) Seed, expand and constrain: three principles for weakly-supervised image segmentation. LNCS 9908:695\u2013711. \nhttps:\/\/doi.org\/10.1007\/978-3-319-46493-0_42","journal-title":"LNCS"},{"key":"4296_CR72","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1109\/CVPR.2017.43","volume":"1","author":"Y Hu","year":"2017","unstructured":"Hu Y, Wang B, Lin S (2017) FC4 fully convolutional color constancy with confidence-weighted pooling. Proc Comput Vis Pattern Recognit 1:330\u2013339. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.43","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"4296_CR73","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.jocs.2018.05.005","volume":"27","author":"Y-D Zhang","year":"2018","unstructured":"Zhang Y-D, Pan Ch, Chen X, Wang F (2018) Abnormal breast identification by nine-layer convolutional neural network with parametric rectified linear unit and rank-based stochastic pooling. J Comput Sci 27:57\u201368. \nhttps:\/\/doi.org\/10.1016\/j.jocs.2018.05.005","journal-title":"J Comput Sci"},{"key":"4296_CR74","doi-asserted-by":"crossref","unstructured":"Qian Y, Woodland PC (2016) Very deep convolutional neural networks for robust speech recognition. \narXiv:1610.00277v1","DOI":"10.1109\/SLT.2016.7846307"},{"key":"4296_CR75","doi-asserted-by":"publisher","unstructured":"Abdel-Hamid O, Mohamed A-R, Jiang H, Penn G. (2012) Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In: Proceedings of international conference on acoustics, speech and signal processing, pp 4277\u20134280. \nhttps:\/\/doi.org\/10.1109\/ICASSP.2012.6288864","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"4296_CR76","doi-asserted-by":"publisher","unstructured":"Sainath T, Mohamed A, Kingsbury B, Ramabhadran B (2013) Deep convolutional neural networks for LVCSR. In: Proceedings of international conference on acoustics, speech and signal processing. \nhttps:\/\/doi.org\/10.1109\/ASRU.2013.6707749","DOI":"10.1109\/ASRU.2013.6707749"},{"issue":"3","key":"4296_CR77","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel A, Hanazawa T, Hinton G, Shikano K, Lang K (1989) Phoneme recognition using time-delay neural networks. IEEE Trans Acoust Speech Signal Process 37(3):328\u2013339. \nhttps:\/\/doi.org\/10.1109\/29.21701","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"4296_CR78","doi-asserted-by":"publisher","unstructured":"Deng L, Abdel-Hamid O, Yu D (2013) A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion. In Proceedings of international conference on acoustics, speech and signal processing, pp 6669\u20136673. \nhttps:\/\/doi.org\/10.1109\/ICASSP.2013.6638952","DOI":"10.1109\/ICASSP.2013.6638952"},{"key":"4296_CR79","unstructured":"Williams T, Li R (2018) Wavelet pooling for convolutional neural networks. In: Proceedings of the international conference on learning representations, vol 6"},{"key":"4296_CR80","unstructured":"Rippel O, Snoek J, Adams RP (2015) Spectral representations for convolutional neural networks. arXiv preprint \narXiv:1506.03767"},{"key":"4296_CR81","doi-asserted-by":"crossref","unstructured":"Xu Y, Kong Q, Wang W, Plumbley MD (2018) Large-scale weakly supervised audio classification using gated convolutional. Neural Netw. \narXiv:1710.00343v1","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"4296_CR82","doi-asserted-by":"publisher","unstructured":"Wang Z, Lan Q, Huang D, Wen M (2016) Combining FFT and spectral-pooling for efficient convolution neural network model. In: Proceeding 2nd International conference on artificial intelligence and industrial engineering, vol 133. \nhttps:\/\/doi.org\/10.2991\/aiie-16.2016.47","DOI":"10.2991\/aiie-16.2016.47"},{"key":"4296_CR83","unstructured":"Zhang H, Ma J (2018) Hartley spectral pooling for deep learning. \narXiv:1810.04028v1"},{"key":"4296_CR84","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-91253-0_23","volume-title":"Artificial Intelligence and Soft Computing","author":"James S. Smith","year":"2018","unstructured":"Smith JS, Wilamowski BM (2018) Discrete cosine transform spectral pooling layers for convolutional neural networks, artificial intelligence and soft computing. ICAISC 2018 (Lecture notes in computer science), vol. 10841. \nhttps:\/\/doi.org\/10.1007\/978-3-319-91253-0_23"},{"key":"4296_CR85","unstructured":"Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2015) Striving for simplicity: the all convolutional net. In: Proceedings of the international conference on learning representations. \narXiv:1412.6806v3"},{"key":"4296_CR86","unstructured":"Li S, Li W, Cook C, Zhu C, Gao Y (2017) A fully trainable network with RNN-based pooling. \narXiv:1706.05157"},{"key":"4296_CR87","doi-asserted-by":"publisher","unstructured":"Sabour S, Frosst N, Hinton G (2018) Matrix capsules with EM routing. In: Proceedings of the international conference on learning representations. \nhttps:\/\/doi.org\/10.13140\/rg.2.2.27416.44800","DOI":"10.13140\/rg.2.2.27416.44800"},{"key":"4296_CR88","doi-asserted-by":"publisher","unstructured":"Tsai Y-H, Hamsici OC, Yang M-H (2015) Adaptive region pooling for object detection. In Proceedings of 2015 IEEE conference on computer vision and pattern recognition, pp 731\u2013739. \nhttps:\/\/doi.org\/10.1109\/CVPR.2015.7298673","DOI":"10.1109\/CVPR.2015.7298673"},{"key":"4296_CR89","unstructured":"Cherian A, Gould S (2018) Second-order temporal pooling for action recognition. \narXiv:1704.06925"},{"key":"4296_CR90","unstructured":"Girdhar R, Ramanan D (2017) Attentional pooling for action recognition. \narXiv:1711.01467v3"},{"key":"4296_CR91","unstructured":"Wang P, Cao Y, Shen C, Liu L, Shen HT (2015) Temporal pyramid pooling based convolutional neural networks for action recognition. \narXiv:1503.01224"},{"key":"4296_CR92","doi-asserted-by":"crossref","unstructured":"Song S, Cheung N-M, Chandrasekhar V, Mandal B (2018) Deep adaptive temporal pooling for activity recognition. \narXiv:1808.07272","DOI":"10.1145\/3240508.3240713"},{"key":"4296_CR93","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1109\/CVPR.2017.172","volume":"1","author":"A Cherian","year":"2017","unstructured":"Cherian A, Fernando B, Harandi M, Gould S (2017) Generalized rank pooling for activity recognition. Proc Comput Vis Pattern Recognit 1:1581\u20131590. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.172","journal-title":"Proc Comput Vis Pattern Recognit"},{"issue":"4","key":"4296_CR94","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TPAMI.2016.2558148","volume":"39","author":"B Fernando","year":"2017","unstructured":"Fernando B, Gavves E, Oramas J, Ghodrati A, Tuytelaars T (2017) Rank pooling for action recognition. IEEE Trans Pattern Anal Mach Int 39(4):773\u2013787. \nhttps:\/\/doi.org\/10.1109\/TPAMI.2016.2558148","journal-title":"IEEE Trans Pattern Anal Mach Int"},{"key":"4296_CR95","doi-asserted-by":"crossref","unstructured":"Fernando B, Gould S (2017), Discriminatively learned hierarchical rank pooling networks. \narXiv:1705.10420v1","DOI":"10.1007\/s11263-017-1030-x"},{"key":"4296_CR96","unstructured":"Wang P, Li W, Gao Z, Tang C, Ogunbona P (2018) Depth pooling based large-scale 3D action recognition with convolutional neural networks. \narXiv:1804.01194"},{"key":"4296_CR97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604","author":"A Kar","year":"2017","unstructured":"Kar A, Rai N, Sikka K, Sharma G (2017) AdaScan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. Proc IEEE Conf Comput Vis Pattern Recognit. \nhttps:\/\/doi.org\/10.1109\/CVPR.2017.604","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"4296_CR98","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2195-1","author":"V Su\u00e1rez-Paniagua","year":"2018","unstructured":"Su\u00e1rez-Paniagua V, Segura-Bedmar I (2018) Evaluation of pooling operations in convolutional architectures for drug-drug interaction extraction. BMC Bioinform. \nhttps:\/\/doi.org\/10.1186\/s12859-018-2195-1","journal-title":"BMC Bioinform"},{"key":"4296_CR99","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast R-CNN. In: International conference on computer vision, pp 1440\u20131448. \nhttps:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"4296_CR100","doi-asserted-by":"crossref","unstructured":"Gulcehre C, Cho K, Pascanu R, Bengio Y (2014) Learned-norm pooling for deep feed forward and recurrent neural networks. \narXiv:1311.1780v7","DOI":"10.1007\/978-3-662-44848-9_34"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04296-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-019-04296-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04296-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T23:42:19Z","timestamp":1593646939000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-019-04296-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,3]]},"references-count":100,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["4296"],"URL":"https:\/\/doi.org\/10.1007\/s00521-019-04296-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,3]]},"assertion":[{"value":"17 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2019","order":3,"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":"Conflict of interest"}}]}}