Meng Hwa Er

knowledge distillation (2) temporal video grounding (2) weakly-supervised learning (2) cross-modal learning (2) self-supervised learning (1) weakly supervised learning (1) multimodal learning (1) video understanding (1) paraphrase generation (1) semantic consistency (1) optical flow (1) unsupervised representation learning (1) skeleton-based action recognition (1) natural language query (1) self-supervised representation learning (1) 3d skeleton cloud (1) temporal order (1) video localization (1) pseudo annotation (1) large language model (1)