![](/data/publis/stil.png)
![](/data/publis/thesis.png)
Improving Latent Representations of ConvNets for Visual Understanding
PhD thesis, Sorbonne Université, Paris (2019) Jury: Stéphane Canu [Reviewer], Greg Mori [Reviewer], Catherine Achard [Examinator], Karteek Alahari [Examinator], David Picard [Examinator], Matthieu Cord [Supervisor], Nicolas Thome [Supervisor]
![](/data/publis/hybridnet.png)
![](/data/publis/shade.png)
SHADE: Information-Based Regularization for Deep Learning
IEEE International Conference on Image Processing (ICIP) (2018) Athens, Greece. Best paper award
![](/data/publis/m2cai.png)
M2CAI workflow challenge: classification of surgical operation steps based on endosopic videos
M2CAI workshop @ MICCAI (2016) Athens, Greece. 2nd best model submitted to the challenge
![](/data/projects/visiir.png)
VISIIR: deep learning for recipe image classification
(2016) Unpublised extension of published work