Fanyi Xiao

object detection (3) self-supervised learning (2) object tracking (2) model compression (2) semantic segmentation (2) image segmentation (2) knowledge distillation (2) segment anything model (2) video segmentation (2) pose estimation (1) contrastive learning (1) transfer learning (1) spectral clustering (1) zero-shot learning (1) egocentric vision (1) image generation (1) weakly supervised learning (1) multi-modal learning (1) video understanding (1) vision transformer (1)