
Samira Ebrahimi Kahou
About
Samira Ebrahimi Kahou’s work spans across several areas in deep learning research including multi-modal learning, knowledge distillation, deep reinforcement learning, and applications. She has made significant contributions to the field of human computer interaction with her work on multi-modal learning for emotion recognition in videos. She has also worked on visual reasoning at the intersection of vision and text. She contributed to the creation of several large-scale benchmarks including FigureQA (visual reasoning on mathematical plots), Something-Something (fine-grained video captioning) and ReDial (conversational movie recommendation). On the application side Samira works on machine learning for disaster response with focus on modeling of extreme weather events.
Awards
- Member of team that won the second place in the PROBA-V Super Resolution Challenge, European Space Agency, 2019
- Best Thesis Award in the Department of Computer Engineering, Polytechnique Montréal, 2017
- Leader of team that won the third place in the Emotion Recognition in the Wild Challenge, ICMI, 2015
- Best Paper Award, ECCV workshop on computer vision with local binary patterns, 2014
- Leader of team that won the first place in the Emotion Recognition in the Wild Challenge, 2013
Relevant Publications
- Li, R., Ebrahimi Kahou, S., Schulz, H., Michalski, V., Charlin, L., & Pal, C. (2018). Towards deep conversational recommendations. Advances in neural information processing systems, 31, 9725-9735.
- Goyal, R., Kahou, S. E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., ... & Memisevic, R. (2017, October). The" Something Something" Video Database for Learning and Evaluating Visual Common Sense. In ICCV (Vol. 1, No. 4, p. 5).
- Kahou, S. E., Bouthillier, X., Lamblin, P., Gulcehre, C., Michalski, V., Konda, K., ... & Bengio, Y. (2016). Emonets: Multimodal deep learning approaches for emotion recognition in video. Journal on Multimodal User Interfaces, 10(2), 99-111.
- Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., & Bengio, Y. (2014). Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550.
Support Us
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta, Ontario, and Quebec as well as foundations, individuals, corporations, and international partner organizations.