Survey on Emotional Body Gesture Recognition

Automatic emotion recognition has become a trending research topic in the past decade. While works based on facial expressions or speech abound, recognizing affect from body gestures remains less explored topic. We present new comprehensive survey hoping to boost field. first introduce emotional as component of what is commonly known ”body language” and comment general aspects gender differences culture dependence. then define complete framework for automatic gesture recognition. person detection static dynamic pose estimation methods both RGB 3D. recent literature related representation learning images emotionally expressive gestures. also discuss multi-modal approaches that combine face with improved pre-processing methodologies (e.g., human estimation) are nowadays mature technologies fully developed robust large scale analysis, we show quantity labelled data scarce. There no agreement clearly defined output spaces representations shallow largely naive geometrical representations.