Gait Based Emotion

Gait-based emotion recognition aims to identify a person's emotional state by analyzing their walking patterns. Current research focuses on developing deep learning models, particularly those employing graph convolutional networks and self-supervised learning techniques, to extract meaningful features from skeletal data representing gait. These advancements improve accuracy in classifying emotions from gait compared to previous methods, leveraging both local and global temporal information within the gait patterns. This field holds significant potential for applications in areas such as mental health monitoring, human-computer interaction, and security systems.