Zhiheng Li

feature learning (2) vision-language model (2) video understanding (2) scene understanding (2) domain generalization (2) bias detection (2) benchmark evaluation (1) semantic segmentation (1) 3d reconstruction (1) pose estimation (1) computer vision (1) zero-shot learning (1) video segmentation (1) object detection (1) knowledge distillation (1) action recognition (1) text-to-image synthesis (1) multimodal learning (1) weakly supervised learning (1) shortcut learning (1)