Siyang Sun

representation learning (1) contrastive learning (1) zero-shot learning (1) semantic segmentation (1) semi-supervised learning (1) few-shot learning (1) domain generalization (1) feature extraction (1) image retrieval (1) prototype learning (1) multimodal learning (1) audio-visual learning (1) cross-modal learning (1) multi-modal learning (1) video understanding (1) object localization (1) semantic embedding (1) masked autoencoder (1) video processing (1) feature enhancement (1)