Ye Yu

transfer learning (2) action recognition (2) contrastive learning (2) video understanding (2) temporal action localization (2) text classification (1) explainable ai (1) adversarial robustness (1) content moderation (1) differentiable rendering (1) multimodal learning (1) self-supervised learning (1) neural architecture search (1) video temporal grounding (1) instruction following (1) video-text alignment (1) weakly-supervised learning (1) parameter-efficient fine-tuning (1) hyperparameter optimization (1) few-shot learning (1)