Qiming ZHANG

vision transformer (3) knowledge distillation (2) hyperspectral image (2) semantic segmentation (2) knowledge transfer (1) self-attention mechanism (1) temporal modeling (1) unsupervised domain adaptation (1) object detection (1) attention mechanism (1) visual perception (1) image reconstruction (1) data augmentation (1) multimodal learning (1) model architecture (1) domain adaptation (1) multi-modal learning (1) human pose estimation (1) semi-supervised learning (1) unsupervised learning (1)