| Fine-grained Video Classification and Captioning. | 1 | 0.35 | 2018 |
| Evaluating visual "common sense" using fine-grained classification and captioning tasks. | 0 | 0.34 | 2018 |
| Generating images with recurrent adversarial networks. | 36 | 3.49 | 2016 |
| Regularizing RNNs by Stabilizing Activations | 0 | 0.34 | 2016 |
| Incorporating long-range consistency in CNN-based texture generation. | 1 | 0.35 | 2016 |
| Architectural Complexity Measures of Recurrent Neural Networks. | 21 | 0.99 | 2016 |
| Conservativeness of Untied Auto-Encoders. | 1 | 0.35 | 2016 |
| Deep Learning Vector Quantization. | 0 | 0.34 | 2016 |
| EmoNets: Multimodal deep learning approaches for emotion recognition in video. | 65 | 1.78 | 2016 |
| Neural Networks with Few Multiplications | 0 | 0.34 | 2015 |
| On Using Very Large Target Vocabulary For Neural Machine Translation | 223 | 10.44 | 2015 |
| The Potential Energy of an Autoencoder | 14 | 0.66 | 2015 |
| Recurrent Neural Networks for Emotion Recognition in Video. | 61 | 1.80 | 2015 |
| RATM: Recurrent Attentive Tracking Model | 15 | 0.59 | 2015 |
| Zero-bias autoencoders and the benefits of co-adapting features | 0 | 0.34 | 2015 |
| Montreal Neural Machine Translation Systems for WMT'15. | 0 | 0.34 | 2015 |
| Deep learning: Architectures, algorithms, applications | 0 | 0.34 | 2015 |
| Real-time activity recognition via deep learning of motion features. | 0 | 0.34 | 2015 |
| Montreal Neural Machine Translation Systems for WMT'15. | 26 | 1.19 | 2015 |
| Regularizing RNNs by Stabilizing Activations | 1 | 0.35 | 2015 |
| Learning Visual Odometry with a Convolutional Network. | 21 | 0.79 | 2015 |
| Dropout as data augmentation. | 12 | 0.71 | 2015 |
| How far can we go without convolution: Improving fully-connected networks. | 3 | 0.46 | 2015 |
| Denoising Criterion for Variational Auto-Encoding Framework | 9 | 0.78 | 2015 |
| Modeling sequential data using higher-order relational features and predictive training. | 5 | 0.46 | 2014 |
| A unified approach to learning depth and motion features | 0 | 0.34 | 2014 |
| The role of spatio-temporal synchrony in the encoding of motion | 0 | 0.34 | 2014 |
| Zero-bias autoencoders and the benefits of co-adapting features. | 0 | 0.34 | 2014 |
| Modeling Deep Temporal Dependencies with Recurrent Grammar Cells"". | 33 | 2.06 | 2014 |
| Combining modality specific deep neural networks for emotion recognition in video | 103 | 3.02 | 2013 |
| The role of spatio-temporal synchrony in the encoding of motion. | 0 | 0.34 | 2013 |
| Feature grouping from spatially constrained multiplicative interaction | 0 | 0.34 | 2013 |
| Learning to relate images. | 44 | 2.28 | 2013 |
| Feature grouping from spatially constrained multiplicative interaction | 1 | 0.35 | 2013 |
| Learning invariant features by harnessing the aperture problem. | 3 | 0.50 | 2013 |
| On autoencoder scoring. | 4 | 0.42 | 2013 |
| Unsupervised learning of depth and motion. | 13 | 1.40 | 2013 |
| Shared Kernel Information Embedding for Discriminative Inference | 18 | 0.83 | 2012 |
| On multi-view feature learning | 8 | 0.62 | 2012 |
| Learning to relate images: Mapping units, complex cells and simultaneous eigenspaces | 2 | 0.43 | 2011 |
| Gradient-based learning of higher-order image features | 31 | 1.37 | 2011 |
| Gated Softmax Classification. | 21 | 0.98 | 2010 |
| Learning to represent spatial transformations with factored higher-order Boltzmann machines. | 110 | 7.13 | 2010 |
| Shared Kernel Information Embedding For Discriminative Inference | 24 | 1.13 | 2009 |
| Unsupervised Learning of Image Transformations | 85 | 6.77 | 2007 |
| Learning to solve QBF | 27 | 1.21 | 2007 |
| Kernel information embeddings | 11 | 1.20 | 2006 |
| Principal surfaces from unsupervised kernel regression. | 41 | 2.39 | 2005 |
| Improving dimensionality reduction with spectral gradient descent. | 5 | 0.57 | 2005 |
| Multiple Relational Embedding | 17 | 1.30 | 2004 |
