activity
20192021
most citedLocal-to-Global Self-Attention in Vision Transformers

22 citations · 31 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV202122 cited

Local-to-Global Self-Attention in Vision Transformers

Jinpeng Li, Yichao Yan, Shengcai Liao +2

Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer mode…

cs.CV20211 cited

When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model

Haibo Jin, Jinpeng Li, Shengcai Liao +1

In recent years, significant progress has been made in the research of facial landmark detection. However, few prior works have thoroughly discussed about models for practical appl…

cs.CV20213 cited

Exploring Visual Context for Weakly Supervised Person Search

Yichao Yan, Jinpeng Li, Shengcai Liao +4

Person search has recently emerged as a challenging task that jointly addresses pedestrian detection and person re-identification. Existing approaches follow a fully supervised set…

cs.CV2020

Generalizable Pedestrian Detection: The Elephant In The Room

Irtiza Hasan, Shengcai Liao, Jinpeng Li +2

Pedestrian detection is used in many vision based applications ranging from video surveillance to autonomous driving. Despite achieving high performance, it is still largely unknow…

cs.CV20195 cited

DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors

Shuai Chen, Jinpeng Li, Chuanqi Yao +4

Traditional neural objection detection methods use multi-scale features that allow multiple detectors to perform detecting tasks independently and in parallel. At the same time, wi…