Wenxuan Xie

large language model (2) representation learning (2) video understanding (2) image classification (1) vision transformer (1) action recognition (1) zero-shot learning (1) object detection (1) self-supervised learning (1) attention mechanism (1) knowledge distillation (1) multimodal learning (1) vision-language alignment (1) image synthesis (1) conditional generation (1) transfer learning (1) visual representation (1) object tracking (1) speech enhancement (1) reinforcement learning (1)