Multimodal behavioral signal processing in the wild
By X. Alameda

Xavier Alameda presents to ADASP research combining signal processing and machine learning to robustly extract low-level features for social signal processing and behavior understanding applications.

Abstract

The automated analysis of human behavior in unstructured scenarios has many potential applications in health care, conflict and people management, sociology, marketing and surveillance. It is therefore unsurprising that many researchers invested efforts into developing computational approaches able to automatically describe the behavior of a group or an individual. Generally speaking, the extraction of high-level traits is unfeasible if the low- and mid-level feature retrieving methods used are not robust and accurate. In this talk I will describe our recent works combining signal processing and machine learning to robustly extract low-level features for three different task with applications to social signal processing and behavior understanding.