Lu Xia

vision language model (3) vision-language model (2) semantic segmentation (1) domain adaptation (1) feature extraction (1) weakly supervised learning (1) multimodal learning (1) source-free domain adaptation (1) 3d scene understanding (1) human pose estimation (1) activity recognition (1) transfer learning (1) open-vocabulary segmentation (1) contrastive learning (1) multimodal large language model (1) visual instruction tuning (1) source-free adaptation (1) pseudo label (1) cross-domain generalization (1) active learning (1)