WonJun Moon

video retrieval (3) contrastive learning (3) text-video alignment (2) prototype learning (2) clip model (2) few-shot learning (2) feature learning (1) vision transformer (1) representation learning (1) embedding learning (1) video recognition (1) video classification (1) attention mechanism (1) weakly supervised learning (1) zero-shot learning (1) fine-grained classification (1) cross-modal retrieval (1) channel attention (1) semantic consistency (1) action recognition (1)