{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T13:15:01Z","timestamp":1762866901572,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2016,8,1]],"date-time":"2016-08-01T00:00:00Z","timestamp":1470009600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61472393","61303150"],"award-info":[{"award-number":["61472393","61303150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The National Science and Technology Major Project of the Ministry of Science and Technology of China","award":["2012GB102007"],"award-info":[{"award-number":["2012GB102007"]}]},{"name":"Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization","award":["13Z02008"],"award-info":[{"award-number":["13Z02008"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1007\/s11042-016-3540-x","type":"journal-article","created":{"date-parts":[[2016,7,31]],"date-time":"2016-07-31T19:58:25Z","timestamp":1469995105000},"page":"11065-11079","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Image classification based on convolutional neural networks with cross-level strategy"],"prefix":"10.1007","volume":"76","author":[{"given":"Yu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zengfu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,1]]},"reference":[{"key":"3540_CR1","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35:1798\u20131828","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3540_CR2","unstructured":"Caffe website: http:\/\/caffe.berkeleyvision.org"},{"key":"3540_CR3","unstructured":"Caffe model zoo: http:\/\/caffe.berkeleyvision.org\/model_zoo.html"},{"key":"3540_CR4","unstructured":"Caffe model zoo wiki page: https:\/\/github.com\/BVLC\/caffe\/wiki\/Model-Zoo"},{"issue":"3","key":"3540_CR5","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"3540_CR6","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE Conference on computer vision and pattern recognition (CVPR), vol 1, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"3540_CR7","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","volume":"18","author":"R Desimone","year":"1995","unstructured":"Desimone R, Duncan J (1995) Neural mechanisms of selective visual attention. Ann Rev Neurosci 18:193\u2013222","journal-title":"Ann Rev Neurosci"},{"key":"3540_CR8","doi-asserted-by":"crossref","first-page":"1610","DOI":"10.1109\/TNN.2010.2066286","volume":"21","author":"J Fan","year":"2010","unstructured":"Fan J, Xu W, Wu Y, Gong Y (2010) Human tracking using convolutional neural networks. IEEE Trans Neural Netw 21:1610\u20131623","journal-title":"IEEE Trans Neural Netw"},{"key":"3540_CR9","doi-asserted-by":"crossref","unstructured":"Freund Y, Schapire R (1995) A desicion-theoretic generalization of on-line learning and an application to boosting. In: Computational learning theory, pp 23\u201337","DOI":"10.1007\/3-540-59119-2_166"},{"key":"3540_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. In: European conference on computer vision (ECCV), pp 346\u2013361","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"3540_CR11","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imageNet classification. arXiv: 1502.01852","DOI":"10.1109\/ICCV.2015.123"},{"key":"3540_CR12","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504\u2013507","journal-title":"Science"},{"key":"3540_CR13","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR (2012) Improving neural net-works by preventing co-adaptation of feature detectors. arXiv: 1207.0580"},{"key":"3540_CR14","unstructured":"ImageNet Website: http:\/\/www.image-net.org\/"},{"key":"3540_CR15","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: ACM International conference on multimedia, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"3540_CR16","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convoluntional neural networks. In: Advances in neural information processing systems (NIPS), vol 25, pp 1106\u20131114"},{"key":"3540_CR17","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE Conference on computer vision and pattern recognition (CVPR), vol 2, pp 2169\u20132178","DOI":"10.1109\/CVPR.2006.68"},{"key":"3540_CR18","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541\u2013551","journal-title":"Neural Comput"},{"key":"3540_CR19","doi-asserted-by":"crossref","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 86:2278\u20132324","journal-title":"Proc IEEE"},{"key":"3540_CR20","doi-asserted-by":"crossref","unstructured":"LeCun Y, Kavukcuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: IEEE International symposium on circuits and systems, pp 254\u2013256","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"3540_CR21","unstructured":"Lee C, Xie S, Gallagher P, Zhang Z, Tu Z (2014) Deeply-supervised networks. arXiv: 1409.5185"},{"key":"3540_CR22","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cviu.2005.09.012","volume":"106","author":"FF Li","year":"2007","unstructured":"Li F F, Fergus R, Perona P (2007) Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput Vis Image Understand 106:59\u201370","journal-title":"Comput Vis Image Understand"},{"key":"3540_CR23","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv: 1312.4400"},{"key":"3540_CR24","doi-asserted-by":"crossref","unstructured":"Liu Y, Yin B, Yu J, Wang Z (2015) Cross-level: a practical strategy for convolutional neural networks based image classification. In: CCF Chinese conference on computer vision, pp 398\u2013406","DOI":"10.1007\/978-3-662-48558-3_40"},{"key":"3540_CR25","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1007\/s11042-012-1289-4","volume":"71","author":"X Long","year":"2014","unstructured":"Long X, Lu H, Li W (2014) Image classification based on nearest neighbor basis vectors. Mulitimed Tools Appl 71:1559\u20131576","journal-title":"Mulitimed Tools Appl"},{"key":"3540_CR26","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91\u2013110","journal-title":"Int J Comput Vis"},{"key":"3540_CR27","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1007\/s11042-012-1107-z","volume":"70","author":"Y Qu","year":"2014","unstructured":"Qu Y, Wu S, Liu H, Xie Y, Wang H (2014) Evaluation of local features and classifiers in BOW model for image classification. Mulitimed Tools Appl 70:605\u2013624","journal-title":"Mulitimed Tools Appl"},{"key":"3540_CR28","doi-asserted-by":"crossref","unstructured":"Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: International joint conference on neural networks, pp 2809\u20132813","DOI":"10.1109\/IJCNN.2011.6033589"},{"key":"3540_CR29","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv: 1409-1556"},{"key":"3540_CR30","doi-asserted-by":"crossref","unstructured":"Sivic J, Zisserman A (2003) Video google: a text retrieval approach to object matching in videos. In: International conference on computer vision (ICCV), pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"3540_CR31","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1016\/0031-3203(92)90062-N","volume":"25","author":"L Spirkovska","year":"1992","unstructured":"Spirkovska L, Reid M B (1992) Robust position, scale, and rotation invariant object recognition using higher-order neural networks. Pattern Recog 25:975\u2013985","journal-title":"Pattern Recog"},{"key":"3540_CR32","doi-asserted-by":"crossref","unstructured":"Sun Y, Wang X, Tang X (2014) Deep learning face representation from predicting 10,000 classes. In: IEEE International conference on computer vision and pattern recognition (CVPR), pp 1891\u20131898","DOI":"10.1109\/CVPR.2014.244"},{"key":"3540_CR33","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. arXiv: 1409-4842"},{"key":"3540_CR34","doi-asserted-by":"crossref","unstructured":"Wang JJ, Yang JC, Yu K, Lv FJ, Huang T, Gong YH (2010) Locality-constrained linear coding for image classification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 3360\u20133367","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"3540_CR35","unstructured":"Yang JC, Yu K, Gong YH, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 1794\u20131801"},{"key":"3540_CR36","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision (ECCV), Part I, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-016-3540-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3540-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3540-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-3540-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,6]],"date-time":"2017-06-06T15:35:54Z","timestamp":1496763354000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-016-3540-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,1]]},"references-count":36,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2017,4]]}},"alternative-id":["3540"],"URL":"https:\/\/doi.org\/10.1007\/s11042-016-3540-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2016,8,1]]}}}