Qijie Xu

Qijie Xu

Auto-generated profile, based on publicly available information

Qijie Xu

Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, School of Computer Science and Technology, Xidian University, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
MDMin Dang
Min Dang
Gang LiuGang Liu
Gang Liu
QXQijie Xu
Qijie Xu
KLKe Li
Ke Li
DWDi Wang
Di Wang
LHLihuo He
Lihuo He

1 March 2024 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
MDMin Dang
Min Dang
Gang LiuGang Liu
Gang Liu
HLHao Li
Hao Li
QXQijie Xu
Qijie Xu
XWXu Wang
Xu Wang
RPRong Pan
Rong Pan

11 June 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HLHao Li
Hao Li
RPRong Pan
Rong Pan
Gang LiuGang Liu
Gang Liu
MDMin Dang
Min Dang
QXQijie Xu
Qijie Xu
BWBo Wan
Bo Wan
The application of oriented object detection in the field of aerial images has gained substantial attention and made significant progress. However, most one-stage object detectors struggle to extract rotation-invariant features of oriented objects using ordinary convolutions. And the structure of two parallel vision subtasks can result in the inconsistency between the classification and regression. In this paper, we propose a Task Integration Based on a Rotated Convolution Kernel Network (TIR-Net) consisting of three modules: Selective Rotation of the Kernel (SRK), Regression Feature Refinement (RFR), and Task Integration (TI). Specifically, SRK module enhances classification features by applying rotated convolution kernels selectively, introducing rotational invariance to the features. RFR module places more emphasis on feature extraction of large aspect ratio objects to improve their perceptibility. TI module integrates classification and regression features to alleviate the inconsistency between classification and regression. Experimental evaluations on the benchmarks for oriented object detection indicate that our method achieves excellent detection performance.

13 October 2025 in Neurocomputing
Verified
Journal Article
Closed access
MDMin Dang
Min Dang
QXQijie Xu
Qijie Xu
Gang LiuGang Liu
Gang Liu
HLHao Li
Hao Li
XWXu Wang
Xu Wang