Zhengrong Xue

point cloud (2) keypoint detection (2) unsupervised learning (2) action recognition (1) domain generalization (1) transfer learning (1) pose estimation (1) self-supervised learning (1) 3d vision (1) policy learning (1) visual reinforcement learning (1) semantic consistency (1) video analysis (1) boundary detection (1) temporal action segmentation (1) pre-trained model (1) synthetic demonstration (1) pre-trained encoder (1) image encoder (1) visuomotor policy (1)