activity
20132023
most citedSingle-Shot Refinement Neural Network for Object Detection

112 citations · 362 across the 23 of their papers we have counts for

collaborators
Showing 2019Show all

10 papers · 1 filter

cs.CV2019

LAMP-HQ: A Large-Scale Multi-Pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

Aijing Yu, Haoxue Wu, Huaibo Huang +2

Near-infrared-visible (NIR-VIS) heterogeneous face recognition matches NIR to corresponding VIS face images. However, due to the sensing gap, NIR images often lose some identity in…

cs.CV2019

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

Shifeng Zhang, Cheng Chi, Yongqiang Yao +2

Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In t…

cs.CV20195 cited

Relational Learning for Joint Head and Human Detection

Cheng Chi, Shifeng Zhang, Junliang Xing +3

Head and human detection have been rapidly improved with the development of deep convolutional neural networks. However, these two tasks are often studied separately without consid…

cs.CV2019

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Cheng Chi, Shifeng Zhang, Junliang Xing +3

Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians. In this paper, we propose an effective and effici…

cs.CV2019

RefineFace: Refinement Neural Network for High Performance Face Detection

Shifeng Zhang, Cheng Chi, Zhen Lei +1

Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists ma…

cs.CV20191 cited

Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation

Chuan-Xian Ren, Bo-Hua Liang, Zhen Lei

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain…