Qing Yu

motion-language model (3) convolutional neural network (2) out-of-distribution detection (2) motion generation (2) cluster analysis (1) self-supervised learning (1) vision transformer (1) question answering (1) transfer learning (1) model evaluation (1) cross-modal learning (1) multi-modal learning (1) unsupervised domain adaptation (1) temporal grounding (1) prompt learning (1) data augmentation (1) video-text alignment (1) instruction tuning (1) human motion (1) cross-modal retrieval (1)