This work presents an explainable affective body expression recognition framework that integrates multi-scale spatiotemporal encoding with LLM-based reasoning. The framework uses MSCMNet to encode body movement patterns across scales, bidirectional …
This work proposes an affective body expression recognition framework that fuses temporal and spatial features from human body movements. The framework combines a body expression energy model, multiscale SPD-based representation learning, and …
This project studies affective body expression recognition through multi-scale spatiotemporal modeling, temporal-spatial feature fusion, and LLM-based reasoning.
This project constructs a multiscale spatio-temporal network for emotion recognition based on full-body motion.
In this project, we propose a novel gait assessment framework to implement non-intrusive, real-time and automatic depression detection using Kinect.