Huaizu Jiang

diffusion model (3) self-supervised learning (2) convolutional neural network (2) scene reconstruction (2) human-object interaction (2) motion estimation (2) optical flow (2) vision-language model (2) transfer learning (1) frame interpolation (1) few-shot learning (1) zero-shot learning (1) knowledge distillation (1) autoregressive generation (1) visual question answering (1) multi-task learning (1) depth estimation (1) supervised learning (1) 3d vision (1) object detection (1)