[19] LI Jia, WANG J. Automatic linguistic indexing of pictures by a statistical modelingapproach[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003,25（9）： 1075一1088.
[20] LUO Jie-bo, SAVAKIS A E, SINGHAL A. A Bayesian network-based frameworkfor semantic image understanding[J]. Pattern Re-cognition, 2005,38（6）： 919-934[21」AKSOY S, KOPERSKIK, TUSK C, etal. Learning Bayesian classifiers for sceneclassification with a visual grammar[J].IEEE Trans on Geoscience and RemoteSensing, 2005,43（3）： 581一589.
[22] HAN Yu-tao, QI Xiao-jun. A complementary SVMs-based image annotationsystem[C]. Proc of International Conference on Image Processing. 2005:1185一1188.
[23] GOH K S, CHANG E Y, LI Bei-tao. Using one-class and two-class SVMs formulticlass image annotation[J]. IEEE Trans on Knowledge and Data Engineering,2005,17（10）： 1333一1346.
[24] Liu W, Sun Y, Zhang H. MiAlbum-a system for home photo managemet using thesemi-automatic image annotation approach[C]. Acm Multimedia Conference.MULTIlVIEDIA '00 Proceedings of the eighth ACM international conference onMultimedia, 2000:479-480.
[25] He X, King O, Ma W Y, et al. Learning a semantic space from user's relevancefeedback for image retrieval[J]. Circuits&Systems for Video Technology IEEETransactions on, 2003, 13（1）：39-48.
[26] Junwei H, Ngan K N, Mingjing L, et al. A memory learning framework foreffective image retrieval. [J]. IEEE Transactions on Image Processing A Publicationof the IEEE Signal Processing Society, 2005, 14（4）：511一524.
[27] SHENHeng-tao, OOIB C, TANK L. Givingmeanings to WWW im-ages[C]. Procof the 8thACM International Conference on Multime-dia. New York: ACM Press,2000: 39-47.
[28] YANG H C, LEE C H. Image semantics discovery from Web pages forsemantic-based image retrieval using self-organizing maps[J]. Expert Systems withApplications, 2008,34（1）： 266-279.
[29] Ames, Morgan, Naaman, Mor. Why we tag: motivations for annotation in mobileand online media[C]. Proceedings of the SIGCHI Conference on Human Factors inComputing Systems. ACM, 2007:971一980.
[30] Rattenbury T, Good N, Naaman M. Towards automatic extraction of event andplace semantics from flickr tags[C]. Proceedings of the 30th annual internationalACM SIGIR conference on Research and development in information retrieval.ACM, 2007:103一110.
[31]朱蓉。基于语义信息的图像理解关键问题研究[J].计算机应用研究，2009,26（4）： 1234:1240.
[32] Hinton G E,Salakhutdinov R R. Reducing the dimensionality of data with neuralnetworks[J]. Science, 2006, 313（5786）： 504-507.
[33] Hinton G E, Osindero S,Teh Y W. A fast learning algorithm for deep belief nets[J].Neural Computation, 2006, 18（7）： 1527-1554.
[34] Vincent P, Larochelle H, Lajoie I, et al. Stacked denoising autoencoders: Learninguseful representations in a deep network with a local denoising criterion[J], TheJournal of Machine Learning Research, 2010, 9999: 3371-3408.
[35] Lee H,Grosse R, Ranganath R,et al. Convolutional deep belief networks forscalable unsupervised learning of hierarchical representations[C]. The 26th AnnualInternational Conference on Machine Learning （ICML 2009）。 Montreal: ACM,2009: 609-616.
[36] Markoff J. How many computers to identi勿a cat? [N] . The New York Times, 2012.
[37] Krizhevsky A, Sutskever I, Hinton G E. ImageNet Classification with DeepConvolutional Neural Networks[C]. 2012 Advances in Neural InformationProcessing Systems（NIPS 2012）。 Lake Tahoe: NIPS foundation, 2012, 1（2）： 4.
[38]李彦宏。2012百度年会主题报告：相信技术的力量[R].北京：百度，2013.
[39] Fan H, Cao Z, Jiang Y, et al. Learning Deep Face Representation[J]. Eprint Arxiv,2014.
[40] Datta R, Joshi D, Li J, et al. Image retrieval: Ideas, influences, and trends of thenew age[J]. Acm Computing Surveys, 2008, 40（2）：2007.
[41」Lee, Honglak, Grosse, Roger, Ranganath, Rajesh, et al. Convolutional deep beliefnetworks for scalable unsupervised learning of hierarchical representations[C].InInternational Conference on Machine Learning. 2009:609-616.
[42] Zeiler M D, Fergus R. Visualizing and Understanding Convolutional Networks[M].Computer Vision一ECCV 2014 Springer International Publishing, 2014:818一833.
[43]马冬梅。基于深度学习的图像检索研究[[D].内蒙古大学，2014.5: 9-10.
[44]夏定元。基于内容的图像检索通用技术研究及应用[D].华中科技大学，2004:46-47.
[44] Moghaddam B, Pentland A. Probabilistic visual learning for object detection[C].Computer Vision, 1995. Proceedings., Fifth International Conference on. IEEE,1995:786-793.
[45] Murphy K, Torralba A, Eaton D, et al. Object Detection and Localization UsingLocal and Global Features.
[46]. Lecture Notes in Computer Science, 2006, 12（1）：20一26.
[47] D. Fox, L. Bo, X. Ren. Kernel Descriptors for Visual Recognition[J]. Advances inNeural Information Processing Systems, 2010.
[48] Norbert, Kriiger, Peter, Janssen, Sinan, Kalkan, et al. Deep hierarchies in theprimate visual cortex: what can we learn for computer vision?[J]. IEEETransactions on Software Engineering, 2013, 35（8）：1847-1871.
[49] Hubel D H, Wiesel T N. Receptive fields, binocular interaction and functionalarchitecture in the cat's visual cortex. [J]. Journal of Physiology, 1962,160（1）：106-154.
[50] D. Marr,Vision. A Computational Investigation into the Human Representation andProcessing of Visual information[M]. Freeman, 1982.
[51」Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets. [J].Neural Computation, 2006, 18（7）：1527-54.
[52] Le, Q.V Building high-level features using large scale unsupervised learning[C].Acoustics, Speech and Signal Processing （ICASSP）， 2013 IEEE InternationalConference on. IEEE, 2011:8595一8598.
[53] Krizhevsky A, Sutskever I, Hinton G E. ImageNet Classification with DeepConvolutional Neural Networks[J]. Advances in Neural Information ProcessingSystems, 2012, 25:2012.
[54] Bo L, Ren X, Fox D. Hierarchical Matching Pursuit for Image Classification:Architecture and Fast Algorithms[J]. Nips, 2011:2115-2123.
[55] Yu K, Lin Y, Lafferty J. Learning image representations from the pixel level viahierarchical sparse coding[C]// Proceedings/CVPR, IEEE Computer SocietyConference on Computer Vision and Pattern Recognition. IEEE Computer SocietyConference on Computer Vision and Pattern Recognition. 2011:1713一1720.
[56] Goh H, Thome N, Cord M, et al. Learning Deep Hierarchical Visual FeatureCoding[J]. IEEE Transactions on Neural Networks&Learning Systems, 2014,25（12）：2212-25.
[57] A. Coates and A. Y Ng. The importance of encoding versus training with sparsecoding and vector quantization[J]. Proceedings of the 28th InternationalConference on Machine Learning, 2011.
[58] Scherer D, Miiller A, Behnke S. Evaluation of Pooling Operations in ConvolutionalArchitectures for Object Recognition.[M]. Artificial Neural Networks2010. Springer Berlin Heidelberg, 2010:92-101.ICANN
[59] Bengio Y Learning Deep Architectures for AI[J]. Foundations&Trends. inMachine Learning, 2009, 2（1）：1一127.
[60] Lee, Honglak, Grosse, Roger, Ranganath, Rajesh, et al. Convolutional deep beliefnetworks for scalable unsupervised learning of hierarchical representations[C]. InInternational Conference on Machine Learning. 2009:609-616.
[61」Krizhevsky A, Sutskever I, Hinton G E. ImageNet Classification with DeepConvolutional Neural Networks[J]. Advances in Neural Information ProcessingSystems, 2012, 25:2012.
[62] Miclut B. Committees of deep feedforward networks trained with few data[J].Lecture Notes in Computer Science, 2014, 8753:736-742.
[63] Bo L, Ren X, Fox D. Unsupervised Feature Learning for RGB-D Based ObjectRecognition[J]. Springer Tracts in Advanced Robotics, 2013, 88:387-402.
[64] Mairal J, Koniusz P, Harchaoui Z, et al. Convolutional Kernel Networks[J].Advances in Neural Information Processing Systems, 2014:2627-2635.
[65] Romero A, Radeva P, Gatta C. Meta-Parameter Free Unsupervised Sparse FeatureLearning[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2015,37（8）：1716-1722.
[66] Li J, Wang J Z. Automatic Linguistic Indexing of Pictures by a statistical modelingapproach[J]. Pattern Analysis&Machine Intelligence IEEE Transactions on, 2003,25（9）：1075一1088.
[67] Chang E, Goh K, Sychay G, et al. CBSA:content-based soft annotation formultimodal image retrieval using bayes point machines[J]. IEEE Transactions onCircuits&Systems for Video Technology, 2003, 13（1）：26-38.
[68」Duygulu P, Barnard K, Freitas J F G D, et al. Object Recognition as MachineTranslation: Learning a Lexicon for a Fixed Image Vocabulary[C]. Proceedings ofthe 7th European Conference on Computer Vision-Part IV. Springer-Verlag,2002:97-112.
[69] Feng S L, Manmatha R, Lavrenko V Multiple Bernoulli relevance models forimage and video annotation[C]. Computer Vision and Pattern Recognition, 2004.CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on.IEEE, 2004:II-1002-II-1009 Vo1.2.
[70] Jeon, J, Lavrenko, V, Manmatha, R. Automatic Image Annotation and Retrievalusing Cross-Media Relevance Models[C]. Proceedings of the 26th InternationalACM SIGIR Conference SIGIR 2003, ACM 2003. 2003:119-126.
[71] Gustavo, Carneiro, Antoni B, Chan, Pedro J, Moreno, et al. Supervised learning ofsemantic classes for image annotation and retrieval. [J]. IEEE Transactions onPattern Analysis&Machine Intelligence, 2007, 29（3）：394-410.
[72] Lavrenko V, Manmatha R, Jeon J. A Model for Learning the Semantics ofPictures[J]. Nips, 2003:553一560.
[73] Y Mori, H. Takahashi, and R. Oka. Image-to-word transformation based ondividing and vector quantizing images with words[C]. MISRII,1999:405-409.
[74] Changhu Wang, Shuicheng Yan, Lei Zhang, et al. Multi-label sparse coding forautomatic image annotation[M]. Multi. IEEE, 2009:1643一1650.
[75] Liu Y, Yang F. Automatic image annotation based on scene semantic trees[J].Journal of Image&Graphics, 2013.
[76] Makadia A, Pavlovic V, Kumar S. A New Baseline for Image Annotation[M].Computer Vision一ECCV 2008. Springer Berlin Heidelberg, 2008:316-329.
[77] Guillaumin M, Mensink T, Verbeek J, et al. TagProp: Discriminative metriclearning in nearest neighbor models for image auto-annotation[C]. ComputerVision, 2009 IEEE 12th International Conference on. IEEE, 2009:309-316.
