Quan Kong

contrastive learning (5) video anomaly detection (4) action recognition (3) self-supervised learning (3) video understanding (3) multimodal learning (2) pose estimation (2) weakly-supervised learning (2) depth estimation (2) trajectory prediction (1) knowledge distillation (1) anomaly detection (1) weakly supervised learning (1) referring expression (1) transfer learning (1) conditional generation (1) human activity recognition (1) multi-modal learning (1) 3d vision (1) computer vision (1)