Dianxi Shi

vision transformer (2) representation learning (1) policy optimization (1) 3d reconstruction (1) contrastive learning (1) monocular depth estimation (1) multi-agent reinforcement learning (1) transfer learning (1) pose estimation (1) event camera (1) self-supervised learning (1) image fusion (1) model-based planning (1) visual localization (1) multi-modal learning (1) visual navigation (1) unsupervised domain adaptation (1) object tracking (1) graph structure (1) deep reinforcement learning (1)