129 citations · 742 across the 38 of their papers we have counts for
5 papers · 1 filter
Rethinking and Designing a High-performing Automatic License Plate Recognition Approach
Yi Wang, Zhen-Peng Bian, Yunhao Zhou +1
In this paper, we propose a real-time and accurate automatic license plate recognition (ALPR) approach. Our study illustrates the outstanding design of ALPR with four insights: (1)…
Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems
Haoliang Li, Yufei Wang, Xiaofei Xie +5
Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdo…
Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
Mantang Guo, Junhui Hou, Jing Jin +2
Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decode…
A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
Yi Wang, Junhui Hou, Xinyu Hou +1
In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are label…
When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks
Zhiyu Zhu, Zhen-Peng Bian, Junhui Hou +2
Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers…