odobez
 

Research

My main research interests are directed along developing statistical models and machine learning algorithms for:

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

Events

Positions:

  • doctoral position in multimedia and computer vision. See page.
  • postdoctoral position in multimedia and computer vision. See page.

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.

I co-organised a workshop on Interactive Human Behavior Analysis in Open or Public Spaces in November 2011 in Amsterdam, as part of the International joint Conference on Ambient Intelligence (AmI).

Recent publications

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.

EYEDIAP: A Database for the Development and Evaluation of Gaze Estimation Algorithms from RGB and RGB-D Cameras
K. Funes, F. Monay and J.-M. Odobez
Proc. Int. Symposium on Eye Tracking Research and Applications, Safety Harbor (US), 2014.

A Conditional Random Field approach for Audio-Visual people diarization
P. Gay, E. Khoury, S. Meignier, J.-M. Odobez and P. Deleglise
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2014.

What to Show? Automatic Stream Selection Among Multiple Sensors
R. Emonet, E. Oberzaucher and J.-M. Odobez
Int. Conf. on Computer Vision Theory and Applications (VISAPP) , January 2014.

Exploiting Scene Cues for Dropped Object Detection
A. Lopez-Mendez, F. Monay and J.-M. Odobez
Int. Conf. on Computer Vision Theory and Applications (VISAPP), January 2014.

A Track Creation and Deletion Framework for Long-Term Online Multi-Face Tracking
S. Duffner and J.-M. Odobez
IEEE Transaction on Image Processing, March 2013.

A Semi-Automated System for Accurate Gaze Coding in Natural Dyadic Interactions
K. Funes, L. Nguyen, D. Gatica-Perez and J.-M. Odobez
Proc. Int. Conf. on Multimodal Interfaces (ICMI), Sydney 2013.

A Sequential Topic Model for Mining Recurrent Activities from Long Term Video Logs
J. Varadarajan, R. Emonet and J.-M. Odobez
Int. Journal of Computer Vision (IJCV), Vol. 103, Num. 1, pages 100-126, May 2013.

Leveraging the Robot Dialog State for Visual Focus of Attention recognition
S. Sheikhi and V. Khalidov and D. Klotz and B. Wrede and J.-M. Odobez
Proc. Int. Conf. on Multimodal Interfaces (ICMI), Sydney 2013.

Person independent 3D gaze estimation from remote RGB-D cameras
K. Funes and J.-M. Odobez
Int. Conf. Image Processing (ICIP), Sept. 2013.

Time-sensitive Topic Models for Action Recognition in Videos
R. Tavenard, R. Emonet and J.-M. Odobez
Int. Conf. Image Processing (ICIP), Sept. 2013.

Fusing Matching and Biometric Similarity Measures for Face Diarization in Video
E. Khoury and P. Gay and J.-M. Odobez
ACM Int. Conf. on Multimedia Retrieval (ICMR), April 2013.

Real-Time Audio-Visual Analysis for Multiperson Videoconferencing
P. Motlicek, S. Duffner, D. Korchagin, H. Bourlard, C. Scheffler, J-M Odobez, G Del Galdo, M. Kallinger and O. Thiergart
Advances in Multimedia, Vol 2013, 2013.

Observation of Vehicle Axles Through Pass-by Noise: A Strategy of Microphone Array Designe
P. Marmaroli, M. Carmona, X. Falourd, J.-M. Odobez and H. Lissek
IEEE Trans. on Intelligent Transportation Systems, Vol.14, Num 4, pp 1654-1664, Dec. 2013.

Bridging the Past, Present and Future: Modeling Scene Activities From Event Relationships and Global Rules
Jagan Varadarajan, Rémi Emonet and Jean-Marc Odobez,
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, June 2012. Supplementary material.

We are not contortionists: coupled adaptive learning for head and body orientation estimation in surveillance video.
Chen Chen and Jean-Marc Odobez,
Oral presentation at IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, June 2012.