C
Canqun Xiang
Researcher at Shenzhen University
Publications - 12
Citations - 244
Canqun Xiang is an academic researcher from Shenzhen University. The author has contributed to research in topics: Object detection & Feature learning. The author has an hindex of 3, co-authored 12 publications receiving 123 citations.
Papers
More filters
Journal ArticleDOI
MS-CapsNet: A Novel Multi-Scale Capsule Network
TL;DR: A multi-scale capsule network that is more robust and efficient for feature representation in image classification and has a competitive performance on FashionMNIST and CIFAR10 datasets is proposed.
Proceedings ArticleDOI
6D-VNet: End-To-End 6DoF Vehicle Pose Estimation From Monocular RGB Images
TL;DR: The proposed 6D-VNet extends Mask R-CNN by adding customised heads for predicting vehicle's finer class, rotation and translation, and takes the spatial neighbouring information into consideration whilst counteracting the effect of extreme gradient values.
Journal ArticleDOI
End-to-End 6DoF Pose Estimation From Monocular RGB Images
TL;DR: Huang et al. as mentioned in this paper proposed 6D-VNet, which extends Mask R-CNN by adding customised heads for predicting vehicle's finer class, rotation and translation.
Journal ArticleDOI
Matrix Capsule Convolutional Projection for Deep Feature Learning
TL;DR: A matrix capsule convolution projection (MCCP) module is proposed by replacing the feature vector with a feature matrix, of which each column represents a local feature, and the CapDetNet is designed to explore the structural information encoding of the MCCP module based on object detection task.
Journal ArticleDOI
SC-RPN: A Strong Correlation Learning Framework for Region Proposal
TL;DR: Wang et al. as discussed by the authors proposed a two-stage strong correlation learning framework, abbreviated as SC-RPN, which aims to set up stronger relationship among different modules in the region proposal task.