Jianxin Ma

disentangled representation (2) multimodal learning (2) image generation (2) representation learning (1) multi-modal learning (1) variational inference (1) temporal modeling (1) image restoration (1) sequence-to-sequence learning (1) image captioning (1) 3d human pose estimation (1) video understanding (1) conditional generation (1) human pose estimation (1) visual grounding (1) transfer learning (1) diffusion model (1) contrastive learning (1) transformer architecture (1) causal inference (1)