Chaoyue Wang

image generation (8) diffusion model (4) generative model (4) generative adversarial network (3) multi-modal learning (3) attention mechanism (2) few-shot learning (2) optical flow (2) semantic segmentation (2) text-to-image generation (2) embedding learning (1) self-supervised learning (1) weakly supervised learning (1) cross-domain learning (1) domain generalization (1) video captioning (1) model architecture (1) video synthesis (1) depth estimation (1) portrait animation (1)