Di Chang

diffusion model (3) face recognition (2) video generation (2) zero-shot learning (2) feature extraction (1) vision language model (1) autoregressive transformer (1) video understanding (1) pose estimation (1) human motion synthesis (1) view consistency (1) temporal coherence (1) cross-domain generalization (1) novel view synthesis (1) human image animation (1) knowledge distillation (1) transfer learning (1) video diffusion model (1) diffusion transformer (1) neural network architecture (1)