Fang Liu

multimodal learning (5) large language model (4) vision-language model (4) semantic segmentation (4) video understanding (4) few-shot learning (3) regret bound (3) clip model (2) graph neural network (2) multi-armed bandit (2) prompt learning (2) upper confidence bound (2) attention mechanism (2) 3d semantic segmentation (2) image restoration (2) domain generalization (2) self-supervised learning (2) weakly supervised learning (2) zero-shot learning (2) aerial scene (2)