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 …
Metaphors are psycholinguistic phenomena that reveal human cognition, yet their neural basis in naturalistic contexts remains underexplored. This study combines electroencephalography (EEG) with MetaPro, a computational metaphor processing tool, to …
This project studies affective body expression recognition through multi-scale spatiotemporal modeling, temporal-spatial feature fusion, and LLM-based reasoning.
This project combines EEG signals and MetaPro-based metaphor processing to study metaphor comprehension in naturalistic language contexts.
This project develops interpretable EEG fusion models that integrate multi-frequency and multi-region brain connectivity patterns for affective brain-computer interfaces.
This project constructs a multiscale spatio-temporal network for emotion recognition based on full-body motion.