Zehan Wang

multi-modal learning (3) vision-language model (3) speech synthesis (3) representation learning (3) speech translation (2) contrastive learning (2) point cloud (2) semantic alignment (2) cross-modal alignment (2) convolutional neural network (2) zero-shot learning (2) scene understanding (2) 3d visual grounding (2) sub-pixel convolution (2) image restoration (2) multimodal learning (2) video super-resolution (2) embedding learning (1) object detection (1) domain generalization (1)