activity
20152022
most citedBoosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features

42 citations · 85 across the 16 of their papers we have counts for

collaborators
Showing cs.CVShow all

17 papers · 1 filter

cs.CV2022

Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Kaidong Li, Ziming Zhang, Cuncong Zhong +1

Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn…

cs.CV20202 cited

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

Usman Sajid, Hasan Sajid, Hongcheng Wang +1

This paper proposes a novel approach for crowd counting in low to high density scenarios in static images. Current approaches cannot handle huge crowd diversity well and thus perfo…

cs.CV20203 cited

Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters

Ziming Zhang, Wenchi Ma, Yuanwei Wu +1

In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively. Recent works on OR showed some promising r…

cs.CV202042 cited

Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features

Feng Cen, Guanghui Wang

Classification of partially occluded images is a highly challenging computer vision problem even for the cutting edge deep learning technologies. To achieve a robust image classifi…

cs.CV20207 cited

Plug-and-Play Rescaling Based Crowd Counting in Static Images

Usman Sajid, Guanghui Wang

Crowd counting is a challenging problem especially in the presence of huge crowd diversity across images and complex cluttered crowd-like background regions, where most previous ap…

cs.CV20198 cited

MDFN: Multi-Scale Deep Feature Learning Network for Object Detection

Wenchi Ma, Yuanwei Wu, Feng Cen +1

This paper proposes an innovative object detector by leveraging deep features learned in high-level layers. Compared with features produced in earlier layers, the deep features are…