Jul'2024
Learning for Companion Robots: Preparation and Adaptation
Nov'2023
Variational Audio-Visual Representation Learning
Sep'2025
From VAE to Diffusion -- probabilistic learning with audio-visual data
Oct'2024
Probabilistic generative models for audio-visual processing
Jan'2023
Unsupervised Probabilistic Learning with Latent Variables
Jun'2021
Deep Generative Modeling of Sequential Data with Dynamical Variational Autoencoders
Feb'2021
Variational Autoencoders for Audio, Visual and Audio-Visual Learning
Sep'2020
Audio-visual variational speech enhancement
Sep'2019
Probabilistic and deep learning for regression in computer vision
Dec'2016
Multimodal human behavior analysis in the wild
Oct'2016
Emerging topics in noisy and missing data
Nov'2025
Multimodal perception, action, and evaluation of socially intelligent robots
Oct'2025
Audio-visual speech processing with probabilistic models
MILA
— Montréal, CA
Jun'2024
Social Robot Learning
CEA List Days
— Saclay, FR
May'2023
Learning for Robots in Conversational Groups
May'2023
Robots within Groups of People
Interdisciplinary Workshop on Mingling Technologies
— TU Delft
Dec'2022
Learning for Socially Intelligent Robots
Computer Science and Electric Engineering Departments, University of Alberta
Feb'2022
Introduction to Dynamical Variational Autoencoders
Jun'2021
Unsupervised Learning for Human Robot Perception
Jun'2021
Towards socially intelligent robots: preliminary results of the H2020 SPRING and the ANR ML3RI projects
May'2021
Unsupervised Audio-Visual Fusion for Upstream Human Behavior Understanding
Jan'2021
Speaker localisation and enhancement in populated environments
ICPR 2020 Workshop on Deep Learning for Human-Centric Activity Understanding
Jan'2021
Combining auditory and visual data to enhance the speech signal
ICPR 2020 Workshop on Multimodal Pattern Recognition for Social Signal Processing
Dec'2020
Towards audio-visual speech enhancement in robotic platforms
Mar'2020
Choosing wisely your deep training loss
Mar'2020
Artificial Intelligence for Social Robots in Gerontological Healthcare
Jul'2019
Significancy & Robustness in Deep Regression
University of Trento
Jul'2019
Probabilistic and deep methods for human behavior understanding
Dec'2018
Multi-speaker audio-visual diarization
SOUND Workshop Bar-Ilan
Oct'2018
Multimodal social behavior understanding
ACM SIGMM Rising Star Lecture at ACM MM
May'2018
Audio-Visual Multiple Speaker with Robotic Platforms
University of Trento and RHUM Workshop
Jun'2016
Matrix completion: a computer vision perspective
Carnegie Mellon University & Digital Video and Multimedia Lab, Columbia University
Jun'2016
Multimodal behavioral signal processing in the wild
Dec'2015
Variational EM and non-linear optimization for multi-sensor scene analysis
Nov'2015
Free-standing conversational groups: the SALSA dataset and multi-modal head and body pose estimation
UPC Image and Video Processing Group & Inria Nancy Team multispeech
Oct'2015
Multimodal Automatic Analysis of Group Behavior