activity
20182021
most citedDETR for Crowd Pedestrian Detection

38 citations · 40 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2021

Phase Space Reconstruction Network for Lane Intrusion Action Recognition

Ruiwen Zhang, Zhidong Deng, Hongsen Lin +1

In a complex road traffic scene, illegal lane intrusion of pedestrians or cyclists constitutes one of the main safety challenges in autonomous driving application. In this paper, w…

cs.LG20212 cited

A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification

Jingyi Wang, Zhidong Deng

Graph convolutional neural network provides good solutions for node classification and other tasks with non-Euclidean data. There are several graph convolutional models that attemp…

cs.CV202038 cited

DETR for Crowd Pedestrian Detection

Matthieu Lin, Chuming Li, Xingyuan Bu +5

Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…

cs.CV2018

Fast Object Detection in Compressed Video

Shiyao Wang, Hongchao Lu, Zhidong Deng

Object detection in videos has drawn increasing attention since it is more practical in real scenarios. Most of the deep learning methods use CNNs to process each decoded frame in…

cs.CV2018

Recent progress in semantic image segmentation

Xiaolong Liu, Zhidong Deng, Yuhan Yang

Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and in…

cs.CV2018

SegStereo: Exploiting Semantic Information for Disparity Estimation

Guorun Yang, Hengshuang Zhao, Jianping Shi +2

Disparity estimation for binocular stereo images finds a wide range of applications. Traditional algorithms may fail on featureless regions, which could be handled by high-level cl…