{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:29:31Z","timestamp":1783711771136,"version":"3.55.0"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s00138-020-01157-3","type":"journal-article","created":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T13:02:47Z","timestamp":1609678967000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Inception recurrent convolutional neural network for object recognition"],"prefix":"10.1007","volume":"32","author":[{"given":"Md Zahangir","family":"Alom","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmudul","family":"Hasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Yakopcic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tarek M.","family":"Taha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijayan K.","family":"Asari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"1157_CR1","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J\u00fcrgen Schmidhuber","year":"2015","unstructured":"Schmidhuber, J\u00fcrgen: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"issue":"6","key":"1157_CR2","first-page":"84","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 60(6), 84\u201390 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1157_CR3","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"key":"1157_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy, C. et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1157_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R. et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1157_CR6","unstructured":"Wang, N. et al.: Transferring rich feature hierarchies for robust visual tracking. arXiv:1501.04587 (2015)"},{"key":"1157_CR7","unstructured":"Mao, J. et al.: Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv:1412.6632 (2014)"},{"key":"1157_CR8","unstructured":"Ballas, N. et al.: Delving deeper into convolutional networks for learning video representations. arXiv:1511.06432 (2015)"},{"issue":"7639","key":"1157_CR9","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M., Thrun, S.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115\u2013118 (2017)","journal-title":"Nature"},{"issue":"22","key":"1157_CR10","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V., Peng, L., Coram, M., Stumpe, M.C., Wu, D., Narayanaswamy, A., Kim, R.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22), 2402\u20132410 (2016)","journal-title":"JAMA"},{"key":"1157_CR11","doi-asserted-by":"crossref","unstructured":"Collobert, R., Jason, W.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning. ACM, (2008)","DOI":"10.1145\/1390156.1390177"},{"key":"1157_CR12","doi-asserted-by":"crossref","unstructured":"Manning, C.D. et al.: The Stanford CoreNLP Natural Language Processing Toolkit. ACL (System Demonstrations). (2014)","DOI":"10.3115\/v1\/P14-5010"},{"issue":"6","key":"1157_CR13","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Magazine 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process Magazine"},{"key":"1157_CR14","unstructured":"Mnih, V. et al.: Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013)"},{"key":"1157_CR15","unstructured":"Lillicrap, T.P. et al.: Continuous control with deep reinforcement learning. arXiv:1509.02971 (2015)"},{"key":"1157_CR16","doi-asserted-by":"crossref","unstructured":"Fukushima, K., Miyake, S.: Neocognitron: a self-organizing neural network model for a mechanism of visual pattern recognition. In: Competition and Cooperation in Neural Nets\u00a0(pp. 267\u2013285). Springer, Berlin (1982)","DOI":"10.1007\/978-3-642-46466-9_18"},{"issue":"11","key":"1157_CR17","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1038\/14819","volume":"2","author":"M Riesenhuber","year":"1999","unstructured":"Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 1019\u20131025 (1999)","journal-title":"Nat. Neurosci."},{"issue":"7","key":"1157_CR18","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1364\/JOSAA.20.001434","volume":"20","author":"TS Lee","year":"2003","unstructured":"Lee, T.S., Mumford, D.: Hierarchical Bayesian inference in the visual cortex. J. Opt. Soc. Am. 20(7), 1434\u20131448 (2003)","journal-title":"J. Opt. Soc. Am."},{"key":"1157_CR19","doi-asserted-by":"crossref","unstructured":"Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning\u00a0(pp. 609\u2013616). ACM (2009)","DOI":"10.1145\/1553374.1553453"},{"issue":"4","key":"1157_CR20","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1111\/j.1460-9568.2004.03528.x","volume":"20","author":"G Deco","year":"2004","unstructured":"Deco, G., Lee, T.S.: The role of early visual cortex in visual integration: a neural model of recurrent interaction. Eur. J. Neurosci. 20(4), 1089\u20131100 (2004)","journal-title":"Eur. J. Neurosci."},{"issue":"3","key":"1157_CR21","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.neuron.2012.01.010","volume":"73","author":"James J DiCarlo","year":"2012","unstructured":"DiCarlo, James J., Zoccolan, Davide, Rust, Nicole C.: How does the brain solve visual object recognition? Neuron 73(3), 415\u2013434 (2012)","journal-title":"Neuron"},{"issue":"4","key":"1157_CR22","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/BF02478259","volume":"5","author":"Warren S McCulloch","year":"1943","unstructured":"McCulloch, Warren S., Pitts, Walter: A logical calculus of the ideas immanent in nervous activity. Bullet. Math. Biophys. 5(4), 115\u2013133 (1943)","journal-title":"Bullet. Math. Biophys."},{"key":"1157_CR23","unstructured":"Fernandez, B., Parlos, A.G., Tsai, W.: Nonlinear dynamic system identification using artificial neural networks (anns). In: International Joint Conference on Neural Networks (IJCNN), (pp. 133\u2013141, 1990)"},{"key":"1157_CR24","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. chapter Learning Internal Representations by Error Propagation, (pp. 318\u2013362). MIT Press, (1986)","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"1157_CR25","doi-asserted-by":"crossref","unstructured":"He, K. et al.: Identity mappings in deep residual networks.In: European Conference on Computer Vision. Springer, (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"1157_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy, C. et al.: Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv:1602.07261 (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1157_CR27","doi-asserted-by":"crossref","unstructured":"He, K. et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1157_CR28","unstructured":"Liang, M., Xiaolin, H.: Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2015)"},{"issue":"11","key":"1157_CR29","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1157_CR30","unstructured":"Lin, M., Qiang, C., Shuicheng, Y.: Network in network. arXiv:1312.4400 (2013)"},{"key":"1157_CR31","unstructured":"Springenberg, J.T. et al.: Striving for simplicity: the all convolutional net. arXiv:1412.6806 (2014)"},{"key":"1157_CR32","unstructured":"Mishkin, D., Jiri, M.: All you need is a good init. arXiv:1511.06422 (2015)"},{"key":"1157_CR33","unstructured":"Chen, T., Goodfellow, I., Shlens, J (2015) Net2net: accelerating learning via knowledge transfer. arXiv:511.05641 (2015)"},{"key":"1157_CR34","unstructured":"Shankar, S. et al.: Refining architectures of deep convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"1157_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C. et al.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1157_CR36","unstructured":"Iandola, F.N. et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and\u2009<\u20090.5\u00a0MB model size. arXiv:1602.07360 (2016)"},{"key":"1157_CR37","unstructured":"Urban, G. et al.: do deep convolutional nets really need to be deep and convolutional? arXiv:1603.05691 (2016)"},{"key":"1157_CR38","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Nikos, K.: Wide residual networks. arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"key":"1157_CR39","unstructured":"Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (elus). arXiv:1511.07289 (2015)"},{"key":"1157_CR40","unstructured":"Koushik, J., Hiroaki, H.:. Improving stochastic gradient descent with feedback. arXiv:1611.01505 (2016)"},{"key":"1157_CR41","unstructured":"Ngiam, J. et al.: On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), (2011)"},{"key":"1157_CR42","doi-asserted-by":"publisher","first-page":"124","DOI":"10.3389\/fpsyg.2013.00124","volume":"4","author":"RC O\u2019Reilly","year":"2013","unstructured":"O\u2019Reilly, R.C., Wyatte, D., Herd, S., Mingus, B., Jilk, D.J.: Recurrent processing during object recognition. Front. Psychol. 4, 124 (2013)","journal-title":"Front. Psychol."},{"issue":"11","key":"1157_CR43","doi-asserted-by":"publisher","first-page":"2248","DOI":"10.1162\/jocn_a_00282","volume":"24","author":"D Wyatte","year":"2012","unstructured":"Wyatte, D., Curran, T., O\u2019Reilly, R.: The limits of feedforward vision: recurrent processing promotes robust object recognition when objects are degraded. J. Cognit. Neurosci. 24(11), 2248\u20132261 (2012)","journal-title":"J. Cognit. Neurosci."},{"key":"1157_CR44","unstructured":"Liao, Q., Poggio, T.: Bridging the gaps between residual learning, recurrent neural networks and visual cortex.\u00a0arXiv:1604.03640, (2016)"},{"key":"1157_CR45","unstructured":"Pinheiro, P.H., Ronan, C. Recurrent convolutional neural networks for scene labeling. In: ICML, (2014)"},{"key":"1157_CR46","doi-asserted-by":"crossref","unstructured":"Donahue, J. et al.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"1157_CR47","first-page":"1","volume":"128","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern recognition. Mach. Learn. 128, 1\u201358 (2006)","journal-title":"Mach. Learn."},{"issue":"12","key":"1157_CR48","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1016\/j.imavis.2004.03.008","volume":"22","author":"Ernst Kussul","year":"2004","unstructured":"Kussul, Ernst, Baidyk, Tatiana: Improved method of handwritten digit recognition tested on MNIST database. Image Vis. Comput. 22(12), 971\u2013981 (2004)","journal-title":"Image Vis. Comput."},{"key":"1157_CR49","unstructured":"Alex, K.: Learning multiple layers of features from tiny images. Technical Report, (2009)"},{"key":"1157_CR50","unstructured":"Netzer, Y. et al.: Reading digits in natural images with unsupervised feature learning. (2011)"},{"issue":"28","key":"1157_CR51","first-page":"1139","volume":"3","author":"I Sutskever","year":"2013","unstructured":"Sutskever, I., et al.: On the importance of initialization and momentum in deep learning. ICML 3(28), 1139\u20131147 (2013)","journal-title":"ICML"},{"issue":"28","key":"1157_CR52","first-page":"1319","volume":"3","author":"IJ Goodfellow","year":"2013","unstructured":"Goodfellow, I.J., et al.: Maxout Networks. ICML 3(28), 1319\u20131327 (2013)","journal-title":"Maxout Networks. ICML"},{"key":"1157_CR53","unstructured":"Wan, L., et al.: Regularization of neural networks using drop-connect. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), (2013)"},{"key":"1157_CR54","unstructured":"Stollenga, M.F. et al.: Deep networks with internal selective attention through feedback connections. Advances in Neural Information Processing Systems, (2014)"},{"key":"1157_CR55","unstructured":"Lee, C.Y. et al.: Deeply-Supervised Nets. AISTATS. Vol. 2, no. 3, (2015)"},{"key":"1157_CR56","unstructured":"Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems. Vol. 2, pp. 2377\u20132385 (2015)"},{"key":"1157_CR57","unstructured":"Springenberg, J.T., Riedmiller, M.: Improving deep neural networks with probabilistic maxout units. In: International Conference on Learning Representations (ICLR), (2014)"},{"key":"1157_CR58","unstructured":"Romero, A. et al.: Fitnets: Hints for thin deep nets. arXiv:1412.6550 (2014)"},{"key":"1157_CR59","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Discriminative transfer learning with tree-based priors. Advances in Neural Information Processing Systems, (2013)"},{"key":"1157_CR60","unstructured":"Ioffe, S., Christian, S.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 (2015)"},{"key":"1157_CR61","unstructured":"Chollet, F.K. https:\/\/github.com\/fchollet\/keras, (2016)"},{"key":"1157_CR62","unstructured":"Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I.J., Bergeron, A., Bouchard, N., Bengio, Y.: Theano: new features and speed improvements. NIPS Workshop on Deep Learning and Unsupervised Feature Learning, (2012)"},{"key":"1157_CR63","doi-asserted-by":"crossref","unstructured":"Huang, G. et al.: Densely connected convolutional networks. arXiv:1608.06993 (2016)","DOI":"10.1109\/CVPR.2017.243"},{"key":"1157_CR64","unstructured":"https:\/\/www.kaggle.com\/c\/tiny-imagenet"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-020-01157-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-020-01157-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-020-01157-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T08:40:37Z","timestamp":1670661637000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-020-01157-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":64,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["1157"],"URL":"https:\/\/doi.org\/10.1007\/s00138-020-01157-3","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"11 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"28"}}