Xiaohan Wang

contrastive learning (6) vision-language model (5) video understanding (5) prototype learning (4) vision language model (3) scene understanding (3) multimodal learning (3) representation learning (3) point cloud (3) zero-shot learning (3) multi-modal learning (2) transformer architecture (2) semantic segmentation (2) cross-modal learning (2) video recognition (2) knowledge editing (2) reinforcement learning (2) action recognition (2) transfer learning (2) domain adaptation (2)