Cheng-Fu Yang

cross-modal learning (3) layout generation (2) scene graph (2) zero-shot learning (1) path planning (1) feature extraction (1) action recognition (1) object recognition (1) self-supervised learning (1) weakly supervised learning (1) image captioning (1) vision-language alignment (1) code generation (1) contextual information (1) test-time adaptation (1) scene understanding (1) visual reasoning (1) few-shot learning (1) feature disentanglement (1) contrastive learning (1)