Peijun Bao

video understanding (2) knowledge distillation (2) weakly-supervised learning (2) cross-modal learning (2) temporal video grounding (2) attention mechanism (1) self-supervised learning (1) transfer learning (1) multimodal learning (1) computer vision (1) 3d human pose estimation (1) paraphrase generation (1) semantic alignment (1) semantic consistency (1) optical flow (1) weakly supervised learning (1) domain adaptation (1) video dataset (1) video moment localization (1) contrastive learning (1)