Wenkang Han

representation learning (1) contrastive learning (1) multimodal learning (1) code generation (1) video understanding (1) text-to-image generation (1) egocentric video (1) cross-attention map (1) attribute binding (1) speech emotion recognition (1) style representation learning (1) coding style (1) transformer-based diffusion (1) personalized code (1) multi-user adaptation (1) self-coherence guidance (1)