| Emonets: Multimodal deep learning approaches for emotion recognition in video SE Kahou, X Bouthillier, P Lamblin, C Gulcehre, V Michalski, K Konda, ... Journal on Multimodal User Interfaces 10, 99-111, 2016 | 483 | 2016 |
| Recurrent neural networks for emotion recognition in video S Ebrahimi Kahou, V Michalski, K Konda, R Memisevic, C Pal Proceedings of the 2015 ACM on international conference on multimodal …, 2015 | 440 | 2015 |
| Combining modality specific deep neural networks for emotion recognition in video SE Kahou, C Pal, X Bouthillier, P Froumenty, Ç Gülçehre, R Memisevic, ... Proceedings of the 15th ACM on International conference on multimodal …, 2013 | 424 | 2013 |
| Learning visual odometry with a convolutional network K Konda, R Memisevic International Conference on Computer Vision Theory and Applications 2, 486-490, 2015 | 200 | 2015 |
| Dropout as data augmentation K Konda, X Bouthillier, R Memisevic, P Vincent stat 1050, 29, 2015 | 150* | 2015 |
| Modeling deep temporal dependencies with recurrent grammar cells"" V Michalski, R Memisevic, K Konda Advances in neural information processing systems 27, 2014 | 130 | 2014 |
| Zero-bias autoencoders and the benefits of co-adapting features K Konda, R Memisevic, D Krueger International conference on learning representations, 2015 | 66 | 2015 |
| How far can we go without convolution: Improving fully-connected networks Z Lin, R Memisevic, K Konda International conference in learning representations Workshop Track, 2016 | 55 | 2016 |
| A unified approach to learning depth and motion features K Konda, R Memisevic Proceedings of the 2014 Indian Conference on Computer Vision Graphics and …, 2014 | 54* | 2014 |
| Real time interaction with mobile robots using hand gestures KR Konda, A Königs, H Schulz, D Schulz Proceedings of the seventh annual ACM/IEEE international conference on Human …, 2012 | 42 | 2012 |
| The role of spatio-temporal synchrony in the encoding of motion. KR Konda, R Memisevic, V Michalski ICLR (Poster), 2014 | 30* | 2014 |
| Unsupervised relational feature learning for vision KR Konda Goethe University Frankfurt, 2016 | 9 | 2016 |
| Building effective deep neural network architectures one feature at a time M Mundt, T Weis, K Konda, V Ramesh arXiv preprint arXiv:1705.06778, 2017 | 1 | 2017 |
| EmoNets: Multimodal deep learning approaches for emotion recognition in video S Ebrahimi Kahou, X Bouthillier, P Lamblin, C Gulcehre, V Michalski, ... arXiv e-prints, arXiv: 1503.01800, 2015 | 1 | 2015 |
| Real-time activity recognition via deep learning of motion features. K Konda, P Chandrashekhariah, R Memisevic, J Triesch ESANN, 2015 | 1 | 2015 |
| Only sparsity based loss function for learning representations V Bakaraju, KR Konda arXiv preprint arXiv:1903.02893, 2019 | | 2019 |
| Building effective deep neural networks one feature at a time M Mundt, T Weis, K Konda, V Ramesh | | 2018 |
