Ming Hu

few-shot learning (3) vision language model (3) semi-supervised learning (3) image classification (3) visual question answering (3) semantic segmentation (3) attention mechanism (3) vision-language model (3) video understanding (2) multimodal large language model (2) data heterogeneity (2) self-supervised learning (2) medical image segmentation (2) medical imaging (2) multimodal learning (2) class imbalance (2) hierarchical classification (1) computer vision (1) action recognition (1) zero-shot learning (1)