My main research interests are on how to endow robots and artificial systems in general with representations of the world allowing them to accurately perceive the world and understand what is going on, in particular during interactions with human, and respond appropriately to human actions. Some of the main tasks we are addressing using machine learning techniques (mainly Bayesian models and deep learning) in this context are for instance:

  • human tracking and activity analysis
  • image and scene representation modeling
  • sequence analysis and multimedia content analysis.


I co-organized a special session on Behavior Imaging in October 2014 at ICIP, Paris.

Festival de Robotique 2013. The 'Perception et Activity Understanding' group presented the results of the european HUMAVIPS project in which he participated in audio-visual perception of people and of their non-verbal behaviors. Link to the boot and some pictures !

I have organised a summer school on Human Activity and Vision in October 2012.

Some recent publications (full list)

HeadFusion: 360 degree Head Pose tracking combining 3D Morphable Model and 3D Reconstruction
Y. Yu, K. Funes and J.-M. Odobez
IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol 40(1), pp 2653-2667, Nov. 2018.

Joint Localization and Classification of Multiple Sound Sources Using a Multi-task Neural Network
W. He, P. Motlicek and J.-M. Odobez
Interspeech, Hyderabad, 2018.

Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization
N. Le and J.-M. Odobez
Interspeech, Hyderabad, 2018.

Real-time Convolutional Networks for Depth-based Human Pose Estimation
A. Martinez, M. Villamizar, O. Canévet and J.-M. Odobez
IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018.

How to Tell Ancient Signs Apart? Recognizing and Visualizing Maya Glyphs with CNNs
G. Can, J.-M. Odobez and D. Gatica
ACM Journal on Computing and Cultural Heritage, accepted for publication 2018.

Towards the Use of Social Interaction Conventions as Prior for Gaze Model Adaptation
R. Siegfried, Y. Yu and J.-M. Odobez
in 19th ACM International Conference on Multimodal Interaction (ICMI), Glasgow, Nov. 2017.

Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition
D. Wu, L. Pigou, P.-J. Kindermans, N. Le, L. Shao, J. Dambre and J.-M. Odobez
IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), Vol. 38(8), pp 1583--1597 2016.

Combining dynamic head pose–gaze mapping with the robot conversational state for attention recognition in human–robot interactions
S.Sheikhi and J.-M. Odobez
Pattern Recognition Letters, Vol. 66, pp 81-90, Nov. 2015.

Exploiting Long-Term Connectivity and Visual Motion in CRF-based Multi-Person Tracking
A. Heili, A. Lopez-Menez and J.-M. Odobez
IEEE Transactions on Image Processing, 23(7):3040-3056, 2014.

Temporal Analysis of Motif Mixtures using Dirichlet Processes
R. Emonet, J. Varadarajan and J.-M. Odobez
IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 36(1):140-156, January 2014.

Leveraging Colour Segmentation for Upper-Body Detection
S. Duffner and J.-M. Odobez
Pattern Recognition, 47(6):2222-2230, 2014.

Geometric Generative Gaze Estimation (G3E) for Remote RGB-D Cameras
K. Funes and J.-M. Odobez
Computer Vision and Pattern Recognition conference (CVPR), 2014.