(Old homepage as placeholder. Will be replaced soon.)
I am currently a PhD candidate at the Montreal Institute for Learning Algorithms (MILA).
My advisors are Pascal Vincent and Doina Precup.
My research focus is on architectures for visual reasoning, modeling of visual time series using recurrent neural networks and model-based reinforcement learning.
Publications
2018
- 2018 Li, R., Ebrahimi Kahou, S., Schulz, H., Michalski, V., Pal, C., Charlin, L.
Towards Deep Conversational Recommendations
Neural Information Processing Systems (NeurIPS 2018)
- 2018 Sharma, S., Suhubdy, D., Michalski, V., Ebrahimi Kahou, S., Bengio, Y.
ChatPainter: Improving Text to Image Generation using Dialogue
International Conference on Learning Representations Workshop (ICLRW 2018)
[pdf]
- 2018 Ebrahimi Kahou, S.*, Michalski, V.*, Atkinson, A., Kádár, Á., Trischler, A., Bengio, Y.
FigureQA: An annotated figure dataset for visual reasoning
International Conference on Learning Representations Workshop (ICLRW 2018)
[pdf][website]
2017
- 2017 Serban, I., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian, S., Kim, T., Pieper, M., Chandar, S., Ke, N., Mudumba, S., de Brebisson, A., Sotelo, J., Suhubdy, D., Michalski, V., Nguyen, A., Pineau, J., Bengio, Y.
A Deep Reinforcement Learning Chatbot
arXiv preprint arXiv:1709.02349
[pdf]
- 2017 Goyal, R., Ebrahimi Kahou, S., Michalski, V., Materzyńska, J. et al.
The "something something" video database for learning and evaluating visual common sense
International Conference On Computer Vision 2017 (ICCV 2017)
[pdf][website]
- 2017 Kahou, S. E., Michalski, V., Memisevic, R., Pal, C., Vincent, P.
RATM: Recurrent Attentive Tracking Model
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops
[pdf] (arXiv preprint arXiv:1510.08660)
2016
- 2016 The Theano Development Team
Theano: A Python framework for fast computation of mathematical expressions
[pdf] (arXiv preprint arXiv:1605.02688)
2015
- 2015 Kahou, S. E., Michalski, V., Konda, K., Memisevic, R., Pal, C.
Recurrent Neural Networks for Emotion Recognition in Video
In proceedings of the 17th ACM International Conference on Multimodal Interaction (ICMI '15)
[pdf][bibtex][code]
- 2015 Kahou, S. E., Bouthillier, X., Lamblin, P., Gulcehre, C., Michalski, V., Konda, K., Jean, S., Froumenty, P., Courville, A., Vincent, P., Memisevic, R., Pal, C., Bengio, Y.
EmoNets: Multimodal deep learning approaches for emotion recognition in video
In Journal on Multimodal User Interfaces, doi:10.1007/s12193-015-0195-2
[pdf] (arXiv preprint arXiv:1503.01800)[bibtex]
2014
- 2014 Michalski, V., Memisevic, R., Konda, K.
Modeling Deep Temporal Dependencies with Recurrent”Grammar Cells”
Neural Information Processing Systems (NIPS 2014)
[pdf]
[supplementary][bibtex]
- 2014 Konda, K., Memisevic, R., Michalski, V.
Learning to encode motion using spatio-temporal synchrony
International Conference on Learning Representations (ICLR 2014)
[pdf][bibtex]
2013
- 2013 Konda K, Memisevic R, Michalski V
Boltzmann machines with dendritic gating.
Bernstein Conference 2013. doi: 10.12751/nncn.bc2013.0160
Contact
Email: [lastname][firstname without last two letters][at]gmail[dot]com