Emotions play a large role in our lives, defining our experiences, and shaping how we view the world and interact with other humans. Perceiving the emotions of social partners helps us understand their behaviors and decide our actions towards them. Human emotion recognition using intelligent systems is an important socio-behavioral task that arises in various applications, including behavior prediction, surveillance,  robotics, affective computing,  etc. Current research in perceiving human emotion predominantly uses facial cues, speech, or physiological signals such as heartbeats and respiration rates. Research in psychology has shown that body expressions are also crucial in emotion expression and perception and that faces alone were not a diagnostic predictor of valence.

In this talk, I will present research on perceptual emotion identification approach for videos of walking individuals. We classify walking individuals from videos into happy, sad, angry, and neutral emotion categories. These emotions represent emotional states that last for an extended period and are more abundant during walking.

Media: https://www.fastcompany.com/90375885/a-new-ai-can-tell-how-you-feel-just-by-watching-you-walk-down-the-street