86 citations · 87 across the 3 of their papers we have counts for
3 papers
cs.CV2021
Vision Pair Learning: An Efficient Training Framework for Image Classification
Bei Tong, Xiaoyuan Yu
Transformer is a potentially powerful architecture for vision tasks. Although equipped with more parameters and attention mechanism, its performance is not as dominant as CNN curre…
cs.CV2021★ 1 cited
A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective
Xin Li, Xin Jin, Jun Fu +3
Collecting amounts of distorted/clean image pairs in the real world is non-trivial, which seriously limits the practical applications of these supervised learning-based methods on…
cs.CV2021★ 86 cited
TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
Shuyuan Li, Huabin Liu, Rui Qian +5
Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradig…