Haidong Zhu

vision-language model (2) 3d reconstruction (1) concept learning (1) image segmentation (1) semi-supervised learning (1) few-shot learning (1) transfer learning (1) object detection (1) attention mechanism (1) multimodal learning (1) person re-identification (1) prompt learning (1) shape recognition (1) graph partitioning (1) zero-shot learning (1) vision language model (1) image classification (1) zero-shot generalization (1) language embedding (1) representation learning (1)