{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T10:05:17Z","timestamp":1776506717741,"version":"3.51.2"},"reference-count":140,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T00:00:00Z","timestamp":1576800000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T00:00:00Z","timestamp":1576800000000},"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":["Prog Artif Intell"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s13748-019-00203-0","type":"journal-article","created":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T21:02:38Z","timestamp":1576875758000},"page":"85-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":973,"title":["Convolutional neural network: a review of models, methodologies and applications to object detection"],"prefix":"10.1007","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3871-2316","authenticated-orcid":false,"given":"Anamika","family":"Dhillon","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2567-3730","authenticated-orcid":false,"given":"Gyanendra K.","family":"Verma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,20]]},"reference":[{"issue":"7553","key":"203_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)","journal-title":"Nature"},{"key":"203_CR2","doi-asserted-by":"crossref","unstructured":"Hong, Z.: A preliminary study on artificial neural network. In: 2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference, vol. 2, pp. 336\u2013338 (2011)","DOI":"10.1109\/ITAIC.2011.6030344"},{"key":"203_CR3","doi-asserted-by":"crossref","unstructured":"Wang, X.J., Zhao, L.L., Wang, S.: A novel SVM video object extraction technology. In: 2012 8th International Conference on Natural Computation, pp. 44\u201348. IEEE (2012)","DOI":"10.1109\/ICNC.2012.6234772"},{"key":"203_CR4","unstructured":"Rish, I.: An empirical study of the naive Bayes classifier. In: IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, vol. 3, no. 22, pp. 41\u201346 (2001)"},{"key":"203_CR5","unstructured":"Islam, N., Zeeshan I., Nazia N.: A survey on optical character recognition system. arXiv preprint arXiv:1710.05703 (2017)"},{"key":"203_CR6","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., WardeFarley, D., Ozair, S., Courville, A.C., Bengio, Y.: Generative adversarial networks. arXiv:1406.2661 (2014)"},{"key":"203_CR7","doi-asserted-by":"crossref","unstructured":"Besbinar, B., Alatan, A.A.: Visual object tracking with autoencoder representations. In: 2016 24th Signal Processing and Communication Application Conference (SIU), pp. 2041\u20132044 (2016)","DOI":"10.1109\/SIU.2016.7496171"},{"issue":"1","key":"203_CR8","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13640-015-0071-8","volume":"2015","author":"X Ma","year":"2015","unstructured":"Ma, X., Geng, J., Wang, H.: Hyperspectral image classification via contextual deep learning. EURASIP J. Image Video Process. 2015(1), 20 (2015)","journal-title":"EURASIP J. Image Video Process."},{"issue":"1","key":"203_CR9","first-page":"926","volume":"9","author":"G Hinton","year":"2010","unstructured":"Hinton, G.: A practical guide to training restricted Boltzmann machines. Momentum 9(1), 926 (2010)","journal-title":"Momentum"},{"issue":"5","key":"203_CR10","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"H Shin","year":"2016","unstructured":"Shin, H., Roth, H.R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., Summers, R.M.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35(5), 1285\u20131298 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"203_CR11","doi-asserted-by":"publisher","first-page":"5632","DOI":"10.1080\/01431161.2016.1246775","volume":"37","author":"W Li","year":"2016","unstructured":"Li, W., Fu, H., Yu, L., Gong, P., Feng, D., Li, C., Clinton, N.: Stacked Autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping. Int. J. Remote Sens. 37, 5632\u20135646 (2016)","journal-title":"Int. J. Remote Sens."},{"key":"203_CR12","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"203_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2808205","volume":"12","author":"F Feng","year":"2015","unstructured":"Feng, F., Wang, X., Li, R.: Correspondence autoencoders for cross-modal retrieval. ACM Trans. Multimed. Comput. Commun. Appl. 12(1), 1\u201322 (2015)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"203_CR14","volume-title":"LNCS 8588\u2014Intelligent Computing Theory","author":"D Hutchison","year":"2014","unstructured":"Hutchison, D.: LNCS 8588\u2014Intelligent Computing Theory. Springer, Berlin (2014)"},{"key":"203_CR15","unstructured":"Koushik, J.: Understanding convolutional neural networks. arXiv preprint arXiv:1605.09081 (2016)"},{"key":"203_CR16","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, pp. 609\u2013616. ACM (2009)","DOI":"10.1145\/1553374.1553453"},{"key":"203_CR17","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193\u2013202 (1980)","journal-title":"Biol. Cybern."},{"key":"203_CR18","doi-asserted-by":"crossref","unstructured":"Papakostas, M., Giannakopoulos, T., Makedon, F., Karkaletsis, V.: Short-term recognition of human activities using convolutional neural networks. In: 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp. 302\u2013307. IEEE (2016)","DOI":"10.1109\/SITIS.2016.56"},{"key":"203_CR19","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1186\/s13640-017-0235-9","volume":"2017","author":"N Yudistira","year":"2017","unstructured":"Yudistira, N., Kurita, T.: Gated spatio and temporal convolutional neural network for activity recognition: towards gated multimodal deep learning. EURASIP J. Image Video Process. 2017, 85 (2017)","journal-title":"EURASIP J. Image Video Process."},{"key":"203_CR20","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2011)"},{"key":"203_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, X., Gong, W., Fu, W., Du, F.: Application of deep learning in object detection. In: 2017 IEEE\/ACIS 16th International Conference on Computer and Information Science (ICIS), pp. 631\u2013634. IEEE (2017)","DOI":"10.1109\/ICIS.2017.7960069"},{"issue":"1","key":"203_CR22","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MSP.2017.2764116","volume":"35","author":"Rajeev Ranjan","year":"2018","unstructured":"Ranjan, R., Sankaranarayanan, S., Bansal, A., Bodla, N., Chen, J.-C., Patel, V.M., Castillo, C.D., Chellappa, R.: Deep learning for understanding faces: machines may be just as good, or better, than humans. IEEE Signal Process. Mag. 35(1), 66\u201383 (2018)","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"203_CR23","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1134\/S1054661817040149","volume":"27","author":"S Milyaev","year":"2017","unstructured":"Milyaev, S., Laptev, I.: Towards reliable object detection in noisy images. Pattern Recognit. Image Anal. 27(4), 713\u2013722 (2017)","journal-title":"Pattern Recognit. Image Anal."},{"key":"203_CR24","doi-asserted-by":"crossref","unstructured":"Zhou, X., Gong, W., Fu, W., Du, F.: Application of deep learning in object detection, pp. 631\u2013634 (2017)","DOI":"10.1109\/ICIS.2017.7960069"},{"issue":"1","key":"203_CR25","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1134\/S1054661816010065","volume":"26","author":"PN Druzhkov","year":"2016","unstructured":"Druzhkov, P.N., Kustikova, V.D.: A survey of deep learning methods and software tools for image classification and object detection. Pattern Recognit. Image Anal. 26(1), 9\u201315 (2016)","journal-title":"Pattern Recognit. Image Anal."},{"key":"203_CR26","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze, V., Chen, Y.-H., Yang, T.-J., Emer, J.S.: Efficient processing of deep neural networks: atutorial and survey. Proc. IEEE 105, 2295\u20132329 (2017)","journal-title":"Proc. IEEE"},{"key":"203_CR27","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.procs.2016.09.126","volume":"100","author":"SU Park","year":"2016","unstructured":"Park, S.U., Park, J.H., Al-masni, M.A., Al-antari, M.A., Uddin, Z., Kim, T.: A depth camera-based human activity recognition via deep learning recurrent neural network for health and social care services. Procedia Comput. Sci. 100, 78\u201384 (2016)","journal-title":"Procedia Comput. Sci."},{"key":"203_CR28","first-page":"29","volume-title":"Sequential deep learning for human action recognition for human action recognition","author":"M Baccouche","year":"2011","unstructured":"Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., Baskurt, A.: Sequential deep learning for human action recognition. In: International workshop on human behavior understanding, pp. 29\u201339. Springer, Berlin, Heidelberg (2011)"},{"issue":"5","key":"203_CR29","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1080\/02564602.2015.1017542","volume":"32","author":"X Zhao","year":"2015","unstructured":"Zhao, X., Shi, X., Zhang, S.: Facial expression recognition via deep learning. IETE Tech. Rev. 32(5), 347\u2013355 (2015)","journal-title":"IETE Tech. Rev."},{"key":"203_CR30","doi-asserted-by":"crossref","unstructured":"Xie, S., Yang, T., Wang, X., Lin, Y.: Hyper-class augmented and regularized deep learning for fine-grained image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2645\u20132654 (2015)","DOI":"10.1109\/CVPR.2015.7298880"},{"key":"203_CR31","unstructured":"Floyd, M.W., Turner, J.T., Aha, D.W.: Using deep learning to automate feature modeling in learning by observation: a preliminary study. In: 2017 AAAI Spring Symposium Series"},{"key":"203_CR32","doi-asserted-by":"crossref","unstructured":"Tang, C., Feng, Y., Yang, X., Zheng, C., Zhou, Y.: The object detection based on deep learning. In: 2017 4th International Conference on Information Science and Control Engineering (ICISCE), pp. 723\u2013728 (2017)","DOI":"10.1109\/ICISCE.2017.156"},{"key":"203_CR33","unstructured":"Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Hasan, M., Van Esesn, B.C., Awwal, A.A.S., Asari, V.K.: The history began from AlexNet: a comprehensive survey on deep learning approaches. arXiv:1803.01164 (2018)"},{"key":"203_CR34","doi-asserted-by":"crossref","unstructured":"Nguyen, H., Maclagan, S.J., Nguyen, T.D., Nguyen, T., Flemons, P., Andrews, K., Ritchie, E.G., Phung, D.: Animal recognition and identification with deep convolutional neural networks for automated wildlife monitoring. In: 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 40\u201349. IEEE (2017)","DOI":"10.1109\/DSAA.2017.31"},{"issue":"25","key":"203_CR35","doi-asserted-by":"publisher","first-page":"E5716","DOI":"10.1073\/pnas.1719367115","volume":"115","author":"MS Norouzzadeh","year":"2018","unstructured":"Norouzzadeh, M.S., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M.S., Packer, C., Clune, J.: Automatically identifying, counting, and describing wild animals incamera-trap images with deep learning. Proc. Nat. Acad. Sci. 115(25), E5716\u2013E5725 (2018)","journal-title":"Proc. Nat. Acad. Sci."},{"key":"203_CR36","doi-asserted-by":"publisher","first-page":"21954","DOI":"10.1109\/ACCESS.2017.2762418","volume":"5","author":"C Yin","year":"2017","unstructured":"Yin, C., Zhu, Y., Fei, J., He, X.: A deep learning approach for intrusion detection using recurrent neural networks. IEEE Access 5, 21954\u201321961 (2017)","journal-title":"IEEE Access"},{"key":"203_CR37","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.neucom.2017.05.012","volume":"275","author":"R Olmos","year":"2018","unstructured":"Olmos, R., Tabik, S., Herrera, F.: Automatic handgun detection alarm in videosusing deep learning. Neurocomputing 275, 66\u201372 (2018)","journal-title":"Neurocomputing"},{"key":"203_CR38","doi-asserted-by":"crossref","unstructured":"Lee, J., Bang, J., Yang, S.I.: Object detection with sliding window in images including multiple similar objects. In: 2017 International Conference on Information and Communication Technology Convergence (ICTC), pp. 803\u2013806 (2017)","DOI":"10.1109\/ICTC.2017.8190786"},{"key":"203_CR39","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","volume":"115","author":"R Zhao","year":"2019","unstructured":"Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., Gao, R.X.: Deep learning and its applications to machine health monitoring. Mech. Syst. Signal Process. 115, 213\u2013237 (2019)","journal-title":"Mech. Syst. Signal Process."},{"key":"203_CR40","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2015)","DOI":"10.1109\/CVPR.2016.91"},{"key":"203_CR41","first-page":"21","volume-title":"Ssd: Single shot multibox detector","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector. In: European conference on computer vision, pp. 21\u201337. Springer, Cham (2016)"},{"key":"203_CR42","doi-asserted-by":"crossref","unstructured":"Li, Y., Ren, F.: Light-Weight RetinaNet for Object Detection. arXiv preprint arXiv:1905.10011 (2019)","DOI":"10.1109\/WF-IoT48130.2020.9221150"},{"key":"203_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999\u20133007 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"203_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. CoRR. arXiv:1612.03144 (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"203_CR45","doi-asserted-by":"crossref","unstructured":"Zhiqiang, W., Jun, L.: A review of object detection based on convolutional neural network. In: 2017 36th Chinese Control Conference (CCC), pp. 11104\u201311109 (2017)","DOI":"10.23919\/ChiCC.2017.8029130"},{"key":"203_CR46","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s11633-017-1053-3","volume":"14","author":"B Zhao","year":"2017","unstructured":"Zhao, B.: A survey on deep learning-based fine-grained object classification and semantic segmentation. Int. J. Autom. Comput. 14, 119\u2013135 (2017)","journal-title":"Int. J. Autom. Comput."},{"key":"203_CR47","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"203_CR48","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3150\u20133158 (2015)","DOI":"10.1109\/CVPR.2016.343"},{"key":"203_CR49","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing System, pp. 91\u201399 (2015)"},{"key":"203_CR50","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"203_CR51","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.patcog.2017.07.026","volume":"72","author":"X Xu","year":"2017","unstructured":"Xu, X., Li, Y., Wu, G., Luo, J.: Multi-modal deep feature learning for RGB-D object detection. Pattern Recognit. 72, 300\u2013313 (2017)","journal-title":"Pattern Recognit."},{"key":"203_CR52","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"1","key":"203_CR53","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/s13640-016-0151-4","volume":"2016","author":"FS Abousaleh","year":"2016","unstructured":"Abousaleh, F.S., Lim, T., Cheng, W.H., Yu, N.H., Anwar Hossain, M., Alhamid, M.F.: A novel comparative deep learning framework for facial age estimation. EURASIP J. Image Video Process. 2016(1), 47 (2016)","journal-title":"EURASIP J. Image Video Process."},{"key":"203_CR54","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1186\/s40537-017-0101-8","volume":"4","author":"X Fang","year":"2017","unstructured":"Fang, X.: Understanding deep learning via back-tracking and deconvolution. J. Big Data 4, 40 (2017)","journal-title":"J. Big Data"},{"key":"203_CR55","unstructured":"Mnih, V., Heess, N., Graves, A.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"issue":"11","key":"203_CR56","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.1109\/TMM.2015.2476655","volume":"17","author":"A Wang","year":"2015","unstructured":"Wang, A., Lu, J., Cai, J., Cham, T., Wang, G.: Large-margin multi-modal deep learning for RGB-D object recognition. IEEE Trans. Multimed. 17(11), 1887\u20131898 (2015)","journal-title":"IEEE Trans. Multimed."},{"key":"203_CR57","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"203_CR58","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"203_CR59","doi-asserted-by":"crossref","unstructured":"Hua, Y., Alahari, K., Schmid, C.: Online object tracking with proposal selection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3092\u20133100 (2015)","DOI":"10.1109\/ICCV.2015.354"},{"issue":"9","key":"203_CR60","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.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"203_CR61","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"203_CR62","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","volume":"35","author":"M Havaei","year":"2017","unstructured":"Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., Pal, C., Jodoin, P.-M., Larochelle, H.: Brain tumor segmentation with deep neural networks. Med. Image Anal. 35, 18\u201331 (2017)","journal-title":"Med. Image Anal."},{"issue":"1","key":"203_CR63","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13640-017-0188-z","volume":"2017","author":"Y Ding","year":"2017","unstructured":"Ding, Y., Cheng, Y., Cheng, X., Li, B., You, X., Yuan, X.: Noise-resistant network: a deep-learning method for face recognition under noise. EURASIP J. Image Video Process. 2017(1), 43 (2017)","journal-title":"EURASIP J. Image Video Process."},{"key":"203_CR64","doi-asserted-by":"crossref","unstructured":"Shan, K., Guo, J., You, W., Lu, D., Bie, R.: Automatic facial expression recognition based on a deep convolutional-neural-network structure. In: 2017 IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA), pp. 123\u2013128 (2017)","DOI":"10.1109\/SERA.2017.7965717"},{"key":"203_CR65","doi-asserted-by":"crossref","unstructured":"Wang, J.G., Mahendran, P.S., Teoh, E.K.: Deep affordance learning for single- and multiple-instance object detection. In: TENCON 2017-2017 IEEE Region 10 Conference, pp. 321\u2013326 (2017)","DOI":"10.1109\/TENCON.2017.8227883"},{"key":"203_CR66","doi-asserted-by":"crossref","unstructured":"Tian, B., Li, L., Qu, Y., Yan, L.: Video object detection for tractability with deeplearning method. In: 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD), pp. 397\u2013401 (2017)","DOI":"10.1109\/CBD.2017.75"},{"key":"203_CR67","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"203_CR68","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"issue":"1","key":"203_CR69","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han, J., Zhang, D., Cheng, G., Liu, N., Xu, D.: Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Process. Mag. 35(1), 84\u2013100 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"203_CR70","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1016\/j.patcog.2017.09.040","volume":"76","author":"M Babaee","year":"2018","unstructured":"Babaee, M., Tung, D., Rigoll, G.: A deep convolutional neural network for video sequence background subtraction. Pattern Recogn. 76, 635\u2013649 (2018)","journal-title":"Pattern Recogn."},{"key":"203_CR71","doi-asserted-by":"crossref","unstructured":"Li, S., Luo, Y., Sun, K., Choi, K.: Heterogeneous system implementation of deep learning neural network for object detection in OpenCL framework. In: 2018 International Conference on Electronics, Information, and Communication (ICEIC), pp. 1\u20134 (2018)","DOI":"10.23919\/ELINFOCOM.2018.8330645"},{"key":"203_CR72","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"Z Wu","year":"2019","unstructured":"Wu, Z., Shen, C., Van Den Hengel, A.: Wider or deeper: revisiting the ResNet model for visual recognition. Pattern Recogn. 90, 119\u2013133 (2019)","journal-title":"Pattern Recogn."},{"key":"203_CR73","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.inffus.2018.09.008","volume":"49","author":"MS Hossain","year":"2019","unstructured":"Hossain, M.S., Muhammad, G.: Emotion recognition using deep learning approach from audio and visual emotional big data. Inf. Fusion 49, 69\u201378 (2019)","journal-title":"Inf. Fusion"},{"issue":"1","key":"203_CR74","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","volume":"41","author":"R Ranjan","year":"2019","unstructured":"Ranjan, R., Patel, V.M., Chellappa, R.: HyperFace: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 121\u2013135 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"203_CR75","first-page":"5","volume":"52","author":"S Zhang","year":"2019","unstructured":"Zhang, S., Yao, L., Sun, A., Tay, Y.I.: Deep learning based recommender system: a survey. ACM Comput. Surv. 52(1), 5 (2019)","journal-title":"ACM Comput. Surv."},{"issue":"11","key":"203_CR76","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Bengio","year":"1998","unstructured":"Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"203_CR77","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"203_CR78","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"203_CR79","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Gao Huang","year":"2016","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: European Conference on Computer Vision, pp. 646\u2013661 (2016)"},{"issue":"1","key":"203_CR80","doi-asserted-by":"publisher","first-page":"207","DOI":"10.3390\/s17010207","volume":"17","author":"SI Oh","year":"2017","unstructured":"Oh, S.I., Kang, H.B.: Object detection and classification by decision-level fusion for intelligent vehicle systems. Sensors 17(1), 207 (2017)","journal-title":"Sensors"},{"key":"203_CR81","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s13640-018-0261-2","volume":"2018","author":"H Xu","year":"2018","unstructured":"Xu, H., Han, Z., Feng, S., Zhou, H., Fang, Y.: Foreign object debris material recognition based on convolutional neural networks. EURASIP J. Image Video Process. 2018, 21 (2018)","journal-title":"EURASIP J. Image Video Process."},{"key":"203_CR82","doi-asserted-by":"publisher","first-page":"10059","DOI":"10.1109\/ACCESS.2016.2639543","volume":"4","author":"HM Bui","year":"2017","unstructured":"Bui, H.M., Lech, M., Cheng, E.V.A., Neville, K., Burnett, I.S.: Object recognition using deep convolutional features transformed by a recursive network structure. IEEE Access 4, 10059\u201310066 (2017)","journal-title":"IEEE Access"},{"key":"203_CR83","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.neucom.2015.12.042","volume":"185","author":"X Jiang","year":"2016","unstructured":"Jiang, X., Pang, Y., Li, X., Pan, J.: Neurocomputing speed up deep neural network based pedestrian detection by sharing features across multi-scale models. Neurocomputing 185, 163\u2013170 (2016)","journal-title":"Neurocomputing"},{"key":"203_CR84","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.image.2016.05.007","volume":"47","author":"D Tom\u00e8","year":"2016","unstructured":"Tom\u00e8, D., Monti, F., Barof, L., Bondi, L., Tagliasacchi, M., Tubaro, S.: Deep convolutional neural networks for pedestrian detection. Signal Process. Image Commun. 47, 482\u2013489 (2016)","journal-title":"Signal Process. Image Commun."},{"key":"203_CR85","first-page":"818","volume-title":"Visualizing and understanding convolutional networks","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818\u2013833. Springer, Cham (2014)"},{"key":"203_CR86","doi-asserted-by":"crossref","unstructured":"Xiao, L., Yan, Q., Deng, S.: Scene classification with improved AlexNet model. In: 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), pp. 1\u20136. IEEE","DOI":"10.1109\/ISKE.2017.8258820"},{"key":"203_CR87","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"7585","key":"203_CR88","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7585), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"203_CR89","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.inffus.2017.10.006","volume":"42","author":"Q Zhang","year":"2018","unstructured":"Zhang, Q., Yang, L.T., Chen, Z., Li, P.: A survey on deep learning for big data. Inf. Fusion 42, 146\u2013157 (2018)","journal-title":"Inf. Fusion"},{"key":"203_CR90","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"203_CR91","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a largescale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"203_CR92","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"203_CR93","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3150\u20133158 (2016)","DOI":"10.1109\/CVPR.2016.343"},{"key":"203_CR94","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-3-319-70090-8_2","volume-title":"Neural Information Processing","author":"Guangxing Han","year":"2017","unstructured":"Han, G., Zhang, X., Li, C.: Revisiting faster r-cnn: a deeper look at region proposal network. In: International Conference on Neural Information Processing, pp. 14\u201324 (2017)"},{"key":"203_CR95","unstructured":"Wu, C.H., Huang, Q., Li, S., Kuo, C.C.J.: A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision. arXiv preprint arXiv:1711.01043"},{"key":"203_CR96","doi-asserted-by":"crossref","unstructured":"Minaee, S., Abdolrashidiy, A., Wang, Y.: An experimental study of deep convolutional features for iris recognition. In: 2016 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), pp. 1\u20136 (2016)","DOI":"10.1109\/SPMB.2016.7846859"},{"key":"203_CR97","doi-asserted-by":"crossref","unstructured":"Li, Q., Jin, S., Yan, J.: Mimicking very efficient network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6356\u20136364 (2017)","DOI":"10.1109\/CVPR.2017.776"},{"key":"203_CR98","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"203_CR99","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, H., Park, E., Cui, X., Kim, H.: Wide-residual-inception networks for real-time object detection. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 758\u2013764 (2017)","DOI":"10.1109\/IVS.2017.7995808"},{"key":"203_CR100","first-page":"37","volume-title":"International Conference on Smart Homes and Health Telematics","author":"C Liu","year":"2016","unstructured":"Liu, C., Cao, Y., Luo, Y., Chen, G., Vokkarane, V., Ma, Y.: Deepfood: deep learning-based food image recognition for computer-aided dietary assessment. In: International Conference on Smart Homes and Health Telematics, pp. 37\u201348. Springer, Cham (2016)"},{"key":"203_CR101","unstructured":"Xia, X., Xu, C., Nan, B.: Inception-v3 for flower classification. In: 2017 2nd International Conference on Image, Vision and Computing (ICIVC), pp. 783\u2013787. IEEE (2017)"},{"key":"203_CR102","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"203_CR103","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"203_CR104","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"203_CR105","unstructured":"Hussain, M., Haque, M.A.: Swishnet: a fast convolutional neural network for speech, music and noise classification and segmentation. arXiv preprint arXiv:1812.00149 (2018)"},{"key":"203_CR106","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/978-3-030-01258-8_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Ligeng Zhu","year":"2018","unstructured":"Zhu, L., Deng, R., Maire, M., Deng, Z., Mori, G., Tan, P.: Sparsely aggregated convolutional networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 186\u2013201 (2018)"},{"key":"203_CR107","doi-asserted-by":"crossref","unstructured":"Zhou, P., Ni, B., Geng, C., Hu, J., Xu, Y.: Scale-transferrable object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 528\u2013537 (2018)","DOI":"10.1109\/CVPR.2018.00062"},{"key":"203_CR108","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"203_CR109","unstructured":"Adam, G., Lorraine, J.: Understanding Neural Architecture Search Techniques. arXiv preprint arXiv:1904.00438 (2019)"},{"key":"203_CR110","unstructured":"Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecturesearch via parameter sharing. arXiv preprint arXiv:1802.03268 (2018)"},{"key":"203_CR111","unstructured":"Chen, Y., Yang, T., Zhang, X., Meng, G., Pan, C., Sun, J.: Detnas: Neural Architecture Search on Object Detection. arXiv preprint arXiv:1903.10979 (2019)"},{"key":"203_CR112","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138710 (2018)","DOI":"10.1109\/CVPR.2018.00907"},{"key":"203_CR113","unstructured":"Tan, M., Le, Q.V.: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv preprint arXiv:1905.11946 (2019)"},{"key":"203_CR114","unstructured":"Google AI Blog: EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling. https:\/\/ai.googleblog.com\/2019\/05\/efficientnet-improvingaccuracy-and.html. Accessed 8 June 2019"},{"key":"203_CR115","doi-asserted-by":"crossref","unstructured":"Torrey, L., Shavlik, J.: Transfer learning. In: Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pp. 242\u2013264. IGI Global (2010)","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"203_CR116","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks?. In: Advances in Neural Information Processing Systems, pp. 3320\u20133328 (2014)"},{"key":"203_CR117","first-page":"270","volume-title":"A survey on deep transfer learning","author":"C Tan","year":"2018","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C.: A survey on deep transfer learning. In: International Conference on Artificial Neural Networks, pp. 270\u2013279. Springer, Cham (2018)"},{"key":"203_CR118","unstructured":"Guignard, L., Weinberger, N.: Animal identification from remote camera images (2016)"},{"key":"203_CR119","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.ecoinf.2017.07.004","volume":"41","author":"AG Villa","year":"2017","unstructured":"Villa, A.G., Salazar, A., Vargas, F.: Towards automatic wild animal monitoring: identification of animal species in camera-trap images using very deep convolutional neural networks. Ecol. Inform. 41, 24\u201332 (2017)","journal-title":"Ecol. Inform."},{"key":"203_CR120","doi-asserted-by":"crossref","unstructured":"Okafor, E., Pawara, P., Karaaba, F., Surinta, O., Codreanu, V., Schomaker, L., Wiering, M.: Comparative study between deep learning and bag of visual words for wild-animal recognition. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/SSCI.2016.7850111"},{"key":"203_CR121","first-page":"220","volume":"2016","author":"Y Fang","year":"2016","unstructured":"Fang, Y., Du, S., Abdoola, R., Djouani, K.: Background categorization for automatic animal detection in aerial videos using neural networks. ANNPR 2016, 220\u2013232 (2016)","journal-title":"ANNPR"},{"issue":"1","key":"203_CR122","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/1687-5281-2013-52","volume":"2013","author":"X Yu","year":"2013","unstructured":"Yu, X., Wang, J., Kays, R., Jansen, P.A., Wang, T., Huang, T.: Automated identification of animal species in camera trap images. EURASIP J. Image Video Process. 2013(1), 52 (2013)","journal-title":"EURASIP J. Image Video Process."},{"key":"203_CR123","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/s11633-017-1085-8","volume":"14","author":"T Zhang","year":"2017","unstructured":"Zhang, T., Xu, H., Hu, Z.: Physiognomy: personality traits prediction by learning. Int. J. Autom. Comput. 14, 386\u2013395 (2017)","journal-title":"Int. J. Autom. Comput."},{"issue":"5","key":"203_CR124","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1080\/02564602.2015.1017542","volume":"32","author":"X Zhao","year":"2015","unstructured":"Zhao, X., Shi, X., Zhang, S., Zhao, X., Shi, X., Zhang, S.: Facial expression recognition via deep learning facial expression recognition via deep learning. IETE Tech. Rev. 32(5), 347\u2013355 (2015)","journal-title":"IETE Tech. Rev."},{"key":"203_CR125","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: Deepface: Closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701\u20131708 (2014)","DOI":"10.1109\/CVPR.2014.220"},{"issue":"6","key":"203_CR126","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1109\/LSP.2018.2822241","volume":"25","author":"B Yoo","year":"2018","unstructured":"Yoo, B., Kwak, Y., Kim, Y., Choi, C., Kim, J.: Multitask learning with weak label expansion. IEEE Signal Process. Lett. 25(6), 808\u2013812 (2018)","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"203_CR127","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3390\/s16010047","volume":"16","author":"M Grega","year":"2016","unstructured":"Grega, M., Matiola\u0144ski, A., Guzik, P., Leszczuk, M.: Automated detection of firearms and knives in a CCTV image. Sensors 16(1), 47 (2016)","journal-title":"Sensors"},{"key":"203_CR128","unstructured":"Lai, J., Maples, S.: Developing a Real-Time Gun Detection Classifier (2017)"},{"key":"203_CR129","doi-asserted-by":"crossref","unstructured":"Anwar, M.K., Risnumawan, A., Darmawan, A., Tamara, M.N., Purnomo, D.S.: Deep multilayer network for automatic targeting system of gun turret. In: 2017 International Electronics Symposium on Engineering Technology and Applications (IES-ETA), pp. 134\u2013139 (2017)","DOI":"10.1109\/ELECSYM.2017.8240392"},{"issue":"12","key":"203_CR130","doi-asserted-by":"publisher","first-page":"4253","DOI":"10.1007\/s11042-013-1537-2","volume":"74","author":"A Glowacz","year":"2015","unstructured":"Glowacz, A., Kmie\u0107, M., Dziech, A.: Visual detection of knives in security applications using active appearance models. Multimedia Tools Appl. 74(12), 4253\u20134267 (2015)","journal-title":"Multimedia Tools Appl."},{"key":"203_CR131","doi-asserted-by":"crossref","unstructured":"Farahnakian, F., Heikkonen, J.: A deep auto-encoder based approach for intrusion detection system. In: 2018 20th International Conference on Advanced Communication Technology (ICACT), pp. 178\u2013183 (2018)","DOI":"10.23919\/ICACT.2018.8323688"},{"key":"203_CR132","doi-asserted-by":"crossref","unstructured":"Ning, X., Zhu, W., Chen, S.: Recognition, object detection and segmentation of white background photos based on deep learning. In: 2017 32nd Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 182\u2013187 (2018)","DOI":"10.1109\/YAC.2017.7967401"},{"key":"203_CR133","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.inffus.2018.11.015","volume":"49","author":"R Olmos","year":"2019","unstructured":"Olmos, R., Tabik, S., Lamas, A., P\u00e9rez-Hern\u00e1ndez, F., Herrera, F.: A binocular image fusion approach for minimizing false positives in handgun detection with deep learning. Inf. Fusion 49, 271\u2013280 (2019)","journal-title":"Inf. Fusion"},{"key":"203_CR134","doi-asserted-by":"crossref","unstructured":"Ning, X., Zhu, W., Chen, S.: Recognition, object detection and segmentation of white background photos based on deep learning, pp. 182\u2013187 (2017)","DOI":"10.1109\/YAC.2017.7967401"},{"key":"203_CR135","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/MM.2018.112130335","volume":"38","author":"T-W Chin","year":"2018","unstructured":"Chin, T.-W., Halpern, M.: Domain-specific approximation for object detection. IEEE Micro 38, 31\u201340 (2018)","journal-title":"IEEE Micro"},{"key":"203_CR136","doi-asserted-by":"publisher","first-page":"8990","DOI":"10.1109\/ACCESS.2018.2795798","volume":"6","author":"W Cao","year":"2018","unstructured":"Cao, W., Yuan, J., He, Z.: Fast deep neural networks with knowledge guided training and predicted regions of interests for real-time video object detection. IEEE Access 6, 8990\u20138999 (2018)","journal-title":"IEEE Access"},{"issue":"4","key":"203_CR137","first-page":"1","volume":"12","author":"Y Liu","year":"2016","unstructured":"Liu, Y., Hua, K.A.: Field effect deep networks for image recognition. ACM Trans. Multimed. Comput. Commun. Appl. 12(4), 1\u201322 (2016)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"8","key":"203_CR138","first-page":"712","volume":"14","author":"E Sangineto","year":"2015","unstructured":"Sangineto, E., Nabi, M., Culibrk, D., Sebe, N.: Self paced deep learning for weakly supervised object detection. IEEE Trans. Pattern Anal. Mach. Intell. 14(8), 712\u2013725 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"203_CR139","doi-asserted-by":"crossref","unstructured":"Bazrafkan, S., Corcoran, P.: Enhancing iris authentication on handheld devices using deep learning derived segmentation techniques. In: 2018 IEEE International Conference on Consumer Electronics (ICCE), pp. 1\u20132 (2018)","DOI":"10.1109\/ICCE.2018.8326219"},{"key":"203_CR140","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1007\/978-3-030-01252-6_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Hongyu Xu","year":"2018","unstructured":"Xu, H., Lv, X., Wang, X., Ren, Z., Bodla, N., Chellappa, R.: Deep regionlets for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 798\u2013814 (2018)"}],"container-title":["Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-019-00203-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13748-019-00203-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-019-00203-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T05:05:17Z","timestamp":1665291917000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13748-019-00203-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,20]]},"references-count":140,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["203"],"URL":"https:\/\/doi.org\/10.1007\/s13748-019-00203-0","relation":{},"ISSN":["2192-6352","2192-6360"],"issn-type":[{"value":"2192-6352","type":"print"},{"value":"2192-6360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,20]]},"assertion":[{"value":"28 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}