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