Hang Chen

audio-visual speech recognition (2) domain adaptation (2) in-context learning (2) causal inference (1) transfer learning (1) speech recognition (1) multi-task learning (1) feature extraction (1) text classification (1) object recognition (1) object detection (1) knowledge distillation (1) social media analysis (1) image restoration (1) semantic segmentation (1) multimodal learning (1) semantic analysis (1) cross-modal learning (1) automatic speech recognition (1) model compression (1)