Xize Cheng

multimodal learning (6) contrastive learning (5) speech synthesis (4) visual speech recognition (3) zero-shot learning (3) point cloud (2) video generation (2) 3d visual grounding (2) audio-visual speech (2) vision-language model (2) speech-to-speech translation (2) domain adaptation (2) transfer learning (2) generative model (2) cross-modal learning (2) speech translation (2) video captioning (1) preference learning (1) object detection (1) domain generalization (1)