Special talk by Abdenour Hadid on Advances in Face Analysis and Beyond

Abstract: Traditional problems in face analysis include the analysis of 2D/3D images for face detection and recognition, facial landmark localization, facial expression recognition, gender and age estimation etc. Significant progress has been achieved in these problems and many commercial systems can already be found in the market. This presentation will discuss some new and appealing problems in face analysis including kinship (family) verification from facial images, health diagnosis from faces, 4D (3D+time) face analysis, spontaneous and micro-expression analysis, face spoofing detection etc. In terms of features and representations, the current tendency is toward using automatically learned features e.g. using deep learning instead of using hand-crafted features. This talk will hopefully be an opportunity for brainstorming around these recent advances in face analysis and beyond.