Institut des Systèmes Intelligents
et de Robotique

Partenariats

UPMC

CNRS

INSERM

Tremplin CARNOT Interfaces

Labex SMART

Rechercher

A voir également

Short bio

bailly Kévin
Title : Associate Professor
Address : 4 place Jussieu, CC 173, 75252 Paris cedex 05
Phone : +33 (0) 1 44 27 63 85
Email : bailly(at)isir.upmc.fr
Group : INTERACTION (INTERACTION)

Vitae (cv - pdf in french)


  • Associate Professor (Maitre de Conférences) at UPMC - ISIR, since 2011
  • Postdoc at Telecom ParisTech - LTCI, 2010-2011
  • Research and Teaching Assistant at UPMC, 2008-2009
  • Ph.D. in Computer Science at UPMC. Supervisors: M. Milgram, 2005-2010
    Subject : Learning-based head pose estimation in still images
  • M.Sc. in Computer Science at University Paris-Est Marne-la-Vallée, 2004

PhD Position


Random Forest / Deep Learning crossover for Facial Expression Recognition : pdf (in french)


Research activities


Applied machine learning and computer vision for automatic face processing :
  • facial action unit detection and intensity estimation
  • multimodal emotion recognition
  • landmark localization
  • head pose estimation

Selected Publications (All publications)


A Dapogny, K Bailly, S Dubuisson. Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit DetectionInternational Journal of Computer Vision
J Nicolle, K Bailly, M Chetouani. Real-Time Facial Action Unit Intensity Prediction with Regularized Metric LearningImage and Vision Computing
A Dapogny, K Bailly, S Dubuisson. Pairwise Conditional Random Forests for facial expression recognition. ICCV 2015
J Nicolle, K Bailly, M Chetouani. Facial Action Unit Intensity Prediction via Hard Multi-Task Metric Learning for Kernel Regression FERA 2015 (winner of the fully automatic intensity challenge)
V Rapp, K Bailly, T Senechal, L Prevost. Multi-Kernel Appearance Model. Image and Vision Computing
J Nicolle, V Rapp, K Bailly, L Prevost, M Chetouani. Robust continuous prediction of human emotions using multiscale dynamic cues. ICMI 2012 (winner of the Audio/Visual Emotion Challenge - AVEC 2012
T Senechal, V Rapp, H Salam, R Seguier, K Bailly, L Prevost Facial Action Recognition Combining Heterogeneous Features via Multikernel Learning. IEEE Trans on SMC-B  (winner of the Facial Expression Recognition and Analysis Challenge - FERA 2011) - 2012
K Bailly, M Milgram, Boosting feature selection for Neural Network based regressionNeural Networks - 2009

PhD Students