Aoxiong Yin

3d visual grounding (2) speech translation (2) sign language translation (2) point cloud (2) video generation (1) self-supervised learning (1) transfer learning (1) knowledge distillation (1) embedding learning (1) machine translation (1) speech synthesis (1) multilingual translation (1) neural machine translation (1) multimodal learning (1) cross-modal learning (1) weakly supervised learning (1) audio-visual learning (1) multi-modal learning (1) video understanding (1) attention mechanism (1)