Taojiannan Yang

video understanding (4) human pose estimation (2) metric learning (2) representation learning (1) domain adaptation (1) vision transformer (1) zero-shot learning (1) action recognition (1) temporal modeling (1) transfer learning (1) data augmentation (1) local learning (1) video segmentation (1) image retrieval (1) object detection (1) few-shot learning (1) multimodal learning (1) feature matching (1) image classification (1) federated learning (1)