Research

I am leading the Perception and Activity Understanding group at the Idiap Research Institue. My main research interests are on human activities analysis from multi-modal data. This entails the investigation of fundamental tasks like the detection and tracking of people, the estimation of their pose or the detection of non-verbal behaviors, and the temporal interpretation of this information in forms of gestures, activities, behavior or social relationships. These tasks are addressed through the design of principled algorithms extending models from computer vision, multimodal signal processing, and machine learning, in particular probabilistic graphical models and deep learning techniques. Surveillance, traffic and human behavior analysis,

Some recent publications (full list)

Robust Unsupervised Gaze Calibration using Conversation and Manipulation Attention Priors
R. Siegfried and J.-M. Odobez
ACM Transactions on Multimedia Computing, Communications, and Applications, Vol. 18(1), pp 20:1-20:27, 2022.

A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings
A. Gupta, S. Tafasca and J.-M. Odobez
CVPR, Int. workshop on Gaze Estimation and Prediction in the Wild, 2022.

A Differential Approach for Gaze Estimation
G. Liu, Y. Yu, K. Funes and J.-M. Odobez
in IEEE Transaction of Pattern Analysis and Machine Intelligence (PAMI), Vol 43(3): 1092-1099, 2021.

Neural Network Adaptation and Data Augmentation for Multi-Speaker Direction-of-Arrival Estimation
W. He, P. Motlicek and J.-M. Odobez
IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol 29:1303-1317, 2021.

Towards an Engagement-Aware Attentive Artificial Listener for Multi-Party Interactions
C. Oertel, P. Jonell, D. Kontogiorgos, K. Funes-Mora, J.-M. Odobez and J. Gustafson
Frontiers in Robotics and AI, Vol. 8, July 2021.

An Efficient Image-to-Image Translation HourGlass-based Architecturefor Object Pushing Policy Learning
M. Ewerton, A.-N. Martinez-Gonzalez and J.-M. Odobez
IEEE/RSJ International Conference on Intelligent Robots and Systems conference (IROS), 2021.

Unsupervised Representation Learning for Gaze Estimation
Y. Yu and J.-M. Odobez
Int Conf. on Vision and Pattern Recognition (CVPR), Seatle, June 2020.

The MuMMER Data Set for Robot Perception in Multi-party HRI Scenarios
O. Canévet, W. He, P. Motlicek and J.-M. Odobez
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Naples, pp 1294-1300 2020.

Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
A. Martinez, M. Villamizar, O. Canévet and J.-M. Odobez
IEEE Trans. on Circuits and System for Video Technology (TCSVT, accepted for publication, Oct 2019), 2020.

Multi-scale sequential network for semantic text segmentation and localization
M. Villamizar, O. Canévet and J.-M. Odobez
Pattern Recognition Letters, Vol. 129, pp 63--69 2020.

WatchNet++: efficient and accurate depth-based network for detecting people attacks and intrusion.
M. Villamizar, A. Martinez-Gonz\'{a}lez, O. Canévet and J.-M. Odobez
Machine Vision and Applications, Vol. 31(6):41 2020.

Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis
Y. Yu, G. Liu and J.-M. Odobez
Int Conf. on Vision and Pattern Recognition (CVPR), Long Beach, June 2019.

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.

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.