activity
20182022
most citedCrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP

4 citations · 4 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV20224 cited

CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP

Mingjie Wang, Jun Zhou, Hao Cai +1

Existing state-of-the-art crowd counting algorithms rely excessively on location-level annotations, which are burdensome to acquire. When only count-level (weak) supervisory signal…

cs.CV2020

STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting

Mingjie Wang, Hao Cai, Xianfeng Han +2

Crowd counting remains a challenging task because the presence of drastic scale variation, density inconsistency, and complex background can seriously degrade the counting accuracy…

cs.CV2020

Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting

Mingjie Wang, Hao Cai, Jun Zhou +1

Crowd counting is an important vision task, which faces challenges on continuous scale variation within a given scene and huge density shift both within and across images. These ch…

cs.LG2018

Multi-scale Convolution Aggregation and Stochastic Feature Reuse for DenseNets

Mingjie Wang, Jun Zhou, Wendong Mao +1

Recently, Convolution Neural Networks (CNNs) obtained huge success in numerous vision tasks. In particular, DenseNets have demonstrated that feature reuse via dense skip connection…

cs.CV2018

Semi-dense Stereo Matching using Dual CNNs

Wendong Mao, Mingjie Wang, Jun Zhou +1

A robust solution for semi-dense stereo matching is presented. It utilizes two CNN models for computing stereo matching cost and performing confidence-based filtering, respectively…

cs.CV2018

3D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Art

Xian-Feng Han, Shi-Jie Sun, Xiang-Yu Song +1

The introduction of inexpensive 3D data acquisition devices has promisingly facilitated the wide availability and popularity of 3D point cloud, which attracts more attention to the…