Dongdong Yu

human pose estimation (4) computer vision (2) keypoint regression (2) spatial attention (2) semantic segmentation (2) siamese network (2) multi-person pose estimation (2) pose estimation (2) object detection (1) contrastive learning (1) transformer architecture (1) sparse representation (1) feature extraction (1) video generation (1) channel attention (1) 3d reconstruction (1) depth estimation (1) budgeted learning (1) multi-task learning (1) in-context learning (1)