2 papers
cs.CV2022
Sequence and Circle: Exploring the Relationship Between Patches
Zhengyang Yu, Jochen Triesch
The vision transformer (ViT) has achieved state-of-the-art results in various vision tasks. It utilizes a learnable position embedding (PE) mechanism to encode the location of each…
cs.CV2020
Self-supervised asymmetric deep hashing with margin-scalable constraint
Zhengyang Yu, Song Wu, Zhihao Dou +1
Due to its effectivity and efficiency, deep hashing approaches are widely used for large-scale visual search. However, it is still challenging to produce compact and discriminative…