Heming Du

multi-modal learning (3) medical imaging (2) instance segmentation (2) gesture recognition (2) semantic segmentation (2) visual navigation (2) human pose estimation (2) point cloud segmentation (2) domain adaptation (1) weakly supervised learning (1) self-attention mechanism (1) self-supervised learning (1) multimodal learning (1) depth estimation (1) object detection (1) action recognition (1) monocular depth estimation (1) uncertainty quantification (1) video understanding (1) 3d vision (1)