Ronald Poppe

Date: 16:00 – 16:30, Thursday, 18.03.2021
Location: MS Teams ICS Colloquium

Title: Deep learning challenges for human behavior analysis
Abstract: The systematic analysis of how we interact with each other face-to-face is essential to study social phenomena. We focus on the long-term goal of providing objective, automated behavior analysis of videos with people in interaction. Significant advances in computer vision and machine learning have led to more robust and fine-grained measurement and interpretation of human behavior. Still, we are a long way from applying our work in practical situations. In this talk, I will outline the most prominent challenges in human behavior analysis and I will illustrate promising directions to address these with our own research.