egbib.bib

@inproceedings{sohn2013learning,
title={Learning and selecting features jointly with point-wise gated $\{$B$\}$ oltzmann machines},
author={Sohn, Kihyuk and Zhou, Guanyu and Lee, Chansoo and Lee, Honglak},
booktitle={Proceedings of The 30th International Conference on Machine Learning},
pages={217--225},
year={2013}
}

1. Neuroscience evidence

@article{Cichy2014Resolving,
author = {Cichy, Radoslaw Martin and Pantazis, Dimitrios and Oliva, Aude},
title = {{Resolving human object recognition in space and time}},
journal = {Nature Publishing Group},
year = {2014},
volume = {17},
number = {3},
pages = {455--462},
month = jan
}

@article{Rust:2010if,
author = {Rust, N C and DiCarlo, J J},
title = {{Selectivity and Tolerance ("Invariance") Both Increase as Visual Information Propagates from Cortical Area V4 to IT}},
journal = {Journal of Neuroscience},
year = {2010},
volume = {30},
number = {39},
pages = {12978--12995},
month = sep
}

@article{Kruger2013Deep,
author = {Kruger, Norbert and Janssen, Peter and Kalkan, Sinan and Lappe, Markus and Leonardis, Ales and Piater, Justus and Rodriguez-Sanchez, Antonio J and Wiskott, Laurenz},
title = {{Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?}},
`journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
`year = {2013},
volume = {35},
number = {8},
pages = {1847--1871}
}

@article{lee2003hierarchical,
  title={Hierarchical Bayesian inference in the visual cortex},
  author={Lee, Tai Sing and Mumford, David},
  journal={JOSA A},
  volume={20},
  number={7},
  pages={1434--1448},
  year={2003},
  publisher={Optical Society of America}
}

Biased Competition Theory
@article{beck2009top,
  title={Top-down and bottom-up mechanisms in biasing competition in the human brain},
  author={Beck, Diane M and Kastner, Sabine},
  journal={Vision research},
  volume={49},
  number={10},
  pages={1154--1165},
  year={2009},
  publisher={Elsevier}
}

@article{desimone1998visual,
  title={Visual attention mediated by biased competition in extrastriate visual cortex},
  author={Desimone, Robert},
  journal={Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences},
  volume={353},
  number={1373},
  pages={1245--1255},
  year={1998},
  publisher={The Royal Society}
}

@article{desimone1995neural,
  title={Neural mechanisms of selective visual attention},
  author={Desimone, Robert and Duncan, John},
  journal={Annual review of neuroscience},
  volume={18},
  number={1},
  pages={193--222},
  year={1995}
}

=====================================

2. Inspiration of deep neural networks

@article{Szegedy:2013vw,
author = {Szegedy, Christian and Zaremba, Wojciech and Sutskever, Ilya and Bruna, Joan and Erhan, Dumitru and Goodfellow, Ian and Fergus, Rob},
title = {{Intriguing properties of neural networks}},
journal = {arXiv.org},
year = {2013},
eprint = {1312.6199v4},
eprinttype = {arxiv},
eprintclass = {cs.CV},
month = dec
}


@incollection{zeiler2014visualizing,
  title={Visualizing and understanding convolutional networks},
  author={Zeiler, Matthew D and Fergus, Rob},
  booktitle={Computer Vision--ECCV 2014},
  pages={818--833},
  year={2014},
  publisher={Springer}
}


@article{Zeiler:2011hy,
author = {Zeiler, M D and Taylor, G W and Fergus, R},
title = {{Adaptive deconvolutional networks for mid and high level feature learning}},
journal = {Computer Vision (ICCV {\ldots}},
year = {2011},
pages = {2018--2025}
}

VGG visualization paper
@article{simonyan2013deep,
  title={Deep inside convolutional networks: Visualising image classification models and saliency maps},
  author={Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew},
  journal={arXiv preprint arXiv:1312.6034},
  year={2013}
}

@inproceedings{le2013building,
  title={Building high-level features using large scale unsupervised learning},
  author={Le, Quoc V},
  booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on},
  pages={8595--8598},
  year={2013},
  organization={IEEE}
}

====================================
3. Convolutional Neural Networks

LeCun's original paper on CNN
@article{lecun1998gradient,
  title={Gradient-based learning applied to document recognition},
  author={LeCun, Yann and Bottou, L{\'e}on and Bengio, Yoshua and Haffner, Patrick},
  journal={Proceedings of the IEEE},
  volume={86},
  number={11},
  pages={2278--2324},
  year={1998},
  publisher={IEEE}
}

@article{jia2014caffe,
  Author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},
  Journal = {arXiv preprint arXiv:1408.5093},
  Title = {Caffe: Convolutional Architecture for Fast Feature Embedding},
  Year = {2014}
}

@booklet{Krizhevsky2012ImageNet,
title = {{ImageNet classification with deep convolutional neural networks}},
author = {Krizhevsky, A and Sutskever, I and Hinton, G E},
year = {2012}
}

Two keypoints in the VGG paper: 1) Depth of neural networks 2) no normalization layers
@article{Simonyan2014Very,
author = {Simonyan, Karen and Zisserman, Andrew},
title = {{Very Deep Convolutional Networks for Large-Scale Image Recognition}},
journal = {arXiv.org},
year = {2014},
eprint = {1409.1556v1},
eprinttype = {arxiv},
eprintclass = {cs.CV},
month = sep
}

Google's GoogLeNet
@article{Szegedy2014Going,
author = {Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew},
title = {{Going Deeper with Convolutions}},
journal = {arXiv.org},
year = {2014},
eprint = {1409.4842v1},
eprinttype = {arxiv},
eprintclass = {cs.CV},
month = sep
}

NIN from NUS
@article{lin2013network,
  title={Network in network},
  author={Lin, Min and Chen, Qiang and Yan, Shuicheng},
  journal={arXiv preprint arXiv:1312.4400},
  year={2013}
}

DBM
@inproceedings{salakhutdinov2009deep,
  title={Deep boltzmann machines},
  author={Salakhutdinov, Ruslan and Hinton, Geoffrey E},
  booktitle={International Conference on Artificial Intelligence and Statistics},
  pages={448--455},
  year={2009}
}


BatchNormalization from Google
@article{ioffe2015batch,
  title={Batch normalization: Accelerating deep network training by reducing internal covariate shift},
  author={Ioffe, Sergey and Szegedy, Christian},
  journal={arXiv preprint arXiv:1502.03167},
  year={2015}
}

PRelu
@article{he2015delving,
  title={Delving deep into rectifiers: Surpassing human-level performance on imagenet classification},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  journal={arXiv preprint arXiv:1502.01852},
  year={2015}
}

Dropout
@article{srivastava2014dropout,
  title={Dropout: A simple way to prevent neural networks from overfitting},
  author={Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
  journal={The Journal of Machine Learning Research},
  volume={15},
  number={1},
  pages={1929--1958},
  year={2014},
  publisher={JMLR. org}
}


====================================
4. Others:

DPM:˜
@article{Felzenszwalb2010Object,
author = {Felzenszwalb, P F and Girshick, R B and McAllester, D and Ramanan, D},
title = {{Object Detection with Discriminatively Trained Part-Based Models}},
journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on},
year = {2010},
volume = {32},
number = {9},
pages = {1627--1645}
}

ImageNet:
@inproceedings{deng2009imagenet,
  title={Imagenet: A large-scale hierarchical image database},
  author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
  booktitle={Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on},
  pages={248--255},
  year={2009},
  organization={IEEE}
}

Representation Learning by Bengio
@article{bengio2013representation,
  title={Representation learning: A review and new perspectives},
  author={Bengio, Yoshua and Courville, Aaron and Vincent, Pascal},
  journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on},
  volume={35},
  number={8},
  pages={1798--1828},
  year={2013},
  publisher={IEEE}
}

====================================
5. Feedback network
Jürgen Schmidhuber's feedback network implemented in rnn
@article{Stollenga:2014tl,
author = {Stollenga, Marijn and Masci, Jonathan and Gomez, Faustino and Schmidhuber, Juergen},
title = {{Deep Networks with Internal Selective Attention through Feedback Connections}},
journal = {arXiv.org},
year = {2014},
eprint = {1407.3068v1},
eprinttype = {arxiv},
eprintclass = {cs.CV},
month = jul
}

@article{sermanet2014attention,
  title={Attention for Fine-Grained Categorization},
  author={Sermanet, Pierre and Frome, Andrea and Real, Esteban},
  journal={arXiv preprint arXiv:1412.7054},
  year={2014}
}

@inproceedings{wang2014attentional,
  title={Attentional Neural Network: Feature Selection Using Cognitive Feedback},
  author={Wang, Qian and Zhang, Jiaxing and Song, Sen and Zhang, Zheng},
  booktitle={Advances in Neural Information Processing Systems},
  pages={2033--2041},
  year={2014}
}

@article{Mnih:2014ti,
author = {Mnih, Volodymyr and Heess, Nicolas and Graves, Alex and Kavukcuoglu, Koray},
title = {{Recurrent Models of Visual Attention}},
journal = {NIPS},
year = {2014},
month = jun
}

DRAW paper from Google DeepMind
@article{gregor2015draw,
  title={DRAW: A Recurrent Neural Network For Image Generation},
  author={Gregor, Karol and Danihelka, Ivo and Graves, Alex and Wierstra, Daan},
  journal={arXiv preprint arXiv:1502.04623},
  year={2015}
}

====================================
6. Detection & Localization
@inproceedings{girshick2014rich,
  title={Rich feature hierarchies for accurate object detection and semantic segmentation},
  author={Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
  booktitle={Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on},
  pages={580--587},
  year={2014},
  organization={IEEE}
}

@inproceedings{erhan2014scalable,
  title={Scalable object detection using deep neural networks},
  author={Erhan, Dumitru and Szegedy, Christian and Toshev, Alexander and Anguelov, Dragomir},
  booktitle={Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on},
  pages={2155--2162},
  year={2014},
  organization={IEEE}
}

Selective Search: region proposals
@article{uijlings2013selective,
  title={Selective search for object recognition},
  author={Uijlings, Jasper RR and van de Sande, Koen EA and Gevers, Theo and Smeulders, Arnold WM},
  journal={International journal of computer vision},
  volume={104},
  number={2},
  pages={154--171},
  year={2013},
  publisher={Springer}
}



@inproceedings{yuri2001interactive,
  title={Interactive graph cuts for optimal boundary and region segmentation of objects in ND images},
  author={Yuri, B and Marie-Pierre, J},
  booktitle={IEEEInternational Conference on Computer Vision. USA: IEEE},
  volume={112},
  year={2001}
}

====================================
7. Recurrent and LSTM
LSTM
@article{hochreiter1997long,
  title={Long short-term memory},
  author={Hochreiter, Sepp and Schmidhuber, J{\"u}rgen},
  journal={Neural computation},
  volume={9},
  number={8},
  pages={1735--1780},
  year={1997},
  publisher={MIT Press}
}

@article{chung2015gated,
  title={Gated Feedback Recurrent Neural Networks},
  author={Chung, Junyoung and Gulcehre, Caglar and Cho, Kyunghyun and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1502.02367},
  year={2015}
}

====================================
8. Max Pooling and invariance
Poggio's max pooling
@article{riesenhuber1999hierarchical,
  title={Hierarchical models of object recognition in cortex},
  author={Riesenhuber, Maximilian and Poggio, Tomaso},
  journal={Nature neuroscience},
  volume={2},
  number={11},
  pages={1019--1025},
  year={1999},
  publisher={Nature Publishing Group}
}
Cresceptron: The very early implementation of max pooling
@inproceedings{weng1992cresceptron,
  title={Cresceptron: a self-organizing neural network which grows adaptively},
  author={Weng, Juyang and Ahuja, Narendra and Huang, Thomas S},
  booktitle={Neural Networks, 1992. IJCNN., International Joint Conference on},
  volume={1},
  pages={576--581},
  year={1992},
  organization={IEEE}
}