Teaching and Talks

Teaching

Fall 2023

• Leaning, Probabilities and Causality with Thomas Hueber, Eric Gaussier and Emilie Devijver. Teaching resources here (while waiting for Chamilo):
  • Notes
  • Slides Introduction
  • Slides Gaussian Mixture Models
  • Slides Hidden Markov Models (T. Hueber)
  • Slides Probabilistic Principal Component Analysis
  • Slides Linear Dynamical Systems
  • Slides Variational AutoEncoders
  • Slides Lab VAE + Slides on Audio Modeling (starting at S32) + Topic + Code skeleton + Data folder
• Advanced Machine Learning: Applications to Vision, Audio and Text with Karteek Alahari, Eric Gaussier, Didier Schwab and Georges Quénot.

Fall 2022

• Leaning, Probabilities and Causality with Thomas Hueber, Eric Gaussier and Emilie Devijver (teaching resources in chamilo).
• Advanced Machine Learning: Applications to Vision, Audio and Text with Karteek Alahari, Eric Gaussier, Didier Schwab and Georges Quénot (teaching resources in chamilo).

Fall 2021

• Fundamentals of Probabilistic Data Mining with Thomas Hueber and Jean-Baptiste Durand (teaching resources in chamilo).
• Machine Learning for Multimodal Data with Karteek Alahari, Eric Gaussier, Didier Schwab and Georges Quénot (teaching resources in chamilo).

Fall 2020

• Fundamentals of Probabilistic Data Mining with Thomas Hueber (teaching resources in chamilo).
• Machine Learning for Computer Vision and Audio Processing (ex Category Learning and Object Recognition) with Karteek Alahari (teaching resources in chamilo).

FALL 2019

• Fundamentals of Probabilistic Data Mining (with Thomas Hueber and Fei Zheng). Course resources at chamilo (login required).
• Category Learning and Object Recognition (with Karteek Alahari and Cordelia Schmidt). Webpage and resources.
• Advanced Learning Models (with Julien Mairal). Webpage and resources.

Fall 2018

• Fundamentals of Probabilistic Data Mining (with Jean-Baptiste Durand).

Talks

Invited Talks

• Variational Audio-Visual Representation Learning, Keynote Talk at ACM International Conference on Multimedia (Nov’23). Slides.
• Learning for Robots in Conversational Groups at Workshop of the International Laboratory on Learning Systems, Universite Paris Saclay (May’23)
• Robots within Groups of People at Interdisciplinary Workshop on Mingling Technologies, TU Delft (May’23)
• Learning for Socially Intelligent Robots at Computer Science and Electric Engineering Departments, University of Alberta (Dec’22)
• Introduction to Dynamical Variational Autoencoders, at MLIA Research Team Seminars (Feb’22)
• Unsupervised Learning for Human Robot Perception at Robotics and AI Summer School 2021 (Jun’21). Online recording.
• Towards socially intelligent robots: preliminary results of the H2020 SPRING and the ANR ML3RI projects at PI Stories University of Trento (Jun’21).
• Unsupervised Audio-Visual Fusion for Upstream Human Behavior Understanding at AI4Media Workshop on New Learning Paradigms and Distributed AI (May’21). Online recording (Starts at 1h09′).
• Variational Autoencoders for Audio, Visual and Audio-Visual Learning at DaSCI Webinars (Feb’21)
• Speaker localisation and enhancement in populated environments at ICPR 2020 Workshop on Deep Learning for Human-Centric Activity Understanding (Jan’21)
• Combining auditory and visual data to enhance the speech signal at ICPR 2020 Workshop on Multimodal pattern recognition for social signal processing in human computer interaction (Jan’21)
• Towards audio-visual speech enhancement in robotic platforms at Journée “perception et interaction homme-robot” du Groupe de Travail GT5 Interactions Personnes / Systèmes Robotiques du GDR Robotique (Dec’20)
• Choosing wisely your deep training loss at Universidade NOVA de Lisboa (March’20)
• Artificial Intelligence for Social Robots in Gerontological Healthcare at European Robotics Forum (March’20)
• Significancy & Robustness in Deep Regression at University of Trento (Jul’19)
• Probabilistic and deep methods for human behavior understanding at Media Integration and Communication Center (Jul’19 )
• Multi-speaker audio-visual diarization at SOUND Workshop Bar-Ilan (Dec’18 )
• Multimodal social behavior understanding at ACM SIGMM Rising Star Lecture at ACM MM (Oct’18 )
• Audio-Visual Multiple Speaker with Robotic Platforms at University of Trento and RHUM Workshop (May’18 )
• Matrix completion: a computer vision perspective at Carnegie Mellon University and Digital Video and Multimedia Lab of Columbia University (Jun’16 )
• Multimodal behavioral signal processing in the wild at Télécom-ParisTech (Jun’16 )
• Variational EM and non-linear optimization for multi-sensor scene analysis at Laboratoire d’Analyse et d’Architecture de Systèmes du CNRS (Dec’15)
• Free-standing conversational groups: the SALSA dataset and multi-modal head and body pose estimation at Universitat Politècnica de Catalunya – Image and Video Processing Group and INRIA Nancy Grand-Est – Team multispeech (Nov’15)
• Multimodal Automatic Analysis of Group Behavior at Workshop on Multimedia Frontiers Lecture (Oct’15)

Tutorials

• Unsupervised Probabilistic Learning with Latent Variables, Machine Learning Summer School Africa 2023 (Jan’23). Slides.
• Deep generative modeling of sequential data with dynamical variational autoencoders at IEEE ICASSP (May’21). Resources.
• Audio-visual variational speech enhancement at Intelligent Sensing Summer School (Sep’20)
• Probabilistic and deep regression for computer vision (ICIAP, Sep’19) [post]
• Multimodal human behavior analysis in the wild (IAPR ICPR, Dec’16)
• Learning from noisy and missing data (ACM Multimedia, Oct’16) [post]