段清｜云南大学｜学者主页

2026

MambaSC: A Feature Matching Method Using Mamba2 with Self and Cross-Attention for Multimodal Images

Rongrui Teng, Yun Liao, W. Wang, Qing Duan, Junhui Liu, Fangwei Jin

Journal of Artificial Intelligence and Soft Computing Research

DOI

2026

SeViMatch: A Detector-Based Image Matching Framework with Semantic-Visual Fusion

Yun Liao, Nan Chen, Junhui Liu, Jiayi Lyu, Zongxiao Hu, Qing Duan

Lecture notes in computer science

DOI

2026

FFMatch: A FilterFormer-Based Network for Accurate Multimodal Image Matching

Yun Liao, Jiayi Lyu, Junhui Liu, Nan Chen, Zhipei Hu, Qing Duan

Lecture notes in computer science

DOI

2026

BiFGA: A Bidirectional Image–Text-Guided Fine-Grained Alignment Method for Remote Sensing Image–Text Retrieval

Yun Liao, Yong Liu, Junhui Liu, Wenbin Tang, Ruiyang Tan, Libin Huang, Qing Duan

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

DOI

2026

Multisemantics-Aware Optimal Feature Matching for Multimodal Remote Sensing Images

Yun Liao, Yide Di, Yu-Nan Liu, Hao Zhou, Xuewen Tan, Junhui Liu, Qing Duan

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

DOI

2026

RSGM: a multi-modal image matching scheme guided by regional semantics

Fangwei Jin, Yun Liao, Junhui Liu, Zongxiao Hu, Xu Qian, Yunpeng Li, Rongrui Teng, Qing Duan

Complex & Intelligent Systems

DOI

2025

面向数字文化产品的虚拟现实人机交互通用路径研究与实践

吕佳依，段清，廖赟，刘俊晖，陈楠，胡宗潇

《印刷与数字媒体技术研究》

DOI

2025

基于UE5和面向微小型团队的虚拟摄制技术实践探索

段清，刘婧如，杨云，刘俊晖，廖赟

《现代电影技术》

2025

UFM: Unified feature matching pre-training with multi-modal image assistants

Yide Di, Yun Liao, Hao Zhou, Kaijun Zhu, Qing Duan, Junhui Liu, Mingyu Lu

PLoS ONE

DOI

2025

A Survey on Neural Radiance Fields

Yun Liao, Yide Di, Hao Zhou, Kaijun Zhu, Mingyu Lu, Qing Duan, Junhui Liu

ACM Computing Surveys

DOI

2025

PMCMatcher: A Parallel Multi-Scale Cascaded Transformer-Based Network for Multimodal Feature Matching

Yun Liao, Jiayi Lyu, Junhui Liu, Nan Chen, Zongxiao Hu, Qing Duan

ACM Multimedia Asia

DOI

2025

Semi-dense feature matching with increased matching amount

Yide Di, Yun Liao, Yu-Nan Liu, Mingyu Lu, Qing Duan, Junhui Liu

The Visual Computer

DOI

2025

WinMRSI: Feature Matching With Window Attention for Multimodal Remote Sensing Image

Yide Di, Yun Liao, Yu-Nan Liu, Hao Zhou, Kaijun Zhu, Mingyu Lu, Qing Duan, Junhui Liu

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

DOI

2025

FmCFA: a feature matching method for critical feature attention in multimodal images

Yun Liao, Xuning Wu, Junhui Liu, Peiyu Liu, Zhixuan Pan, Qing Duan

Scientific Reports

DOI

2025

MSSA: A Multi-Scale Semantic-Aware Method for Remote Sensing Image–Text Retrieval

Yun Liao, Zongxiao Hu, Fangwei Jin, Junhui Liu, Nan Chen, Jiayi Lv, Qing Duan

Remote Sensing

DOI

2024

Local feature matching from detector-based to detector-free: a survey

Yun Liao, Yide Di, Kaijun Zhu, Hao Zhou, Ming-Yu Lu, Yi-Jia Zhang, Qing Duan, Junhui Liu

Applied intelligence (Boston)

DOI

2024

Using scale-equivariant CNN to enhance scale robustness in feature matching

Yun Liao, Peiyu Liu, Xuning Wu, Zhixuan Pan, Kaijun Zhu, Hao Zhou, Junhui Liu, Qing Duan

The Visual Computer

DOI

2023

MIVI: multi-stage feature matching for infrared and visible image

Yide Di, Yun Liao, Kaijun Zhu, Hao Zhou, Yi-Jia Zhang, Qing Duan, Junhui Liu, Ming-Yu Lu

The Visual Computer

DOI

2023

FeMIP: detector-free feature matching for multimodal images with policy gradient

Yide Di, Yun Liao, Hao Zhou, Kaijun Zhu, Yi-Jia Zhang, Qing Duan, Junhui Liu, Ming-Yu Lu

Applied intelligence (Boston)

DOI

2022

SMDAF: A novel keypoint based method for copy-move forgery detection

Guangyu Yue, Qing Duan, Renyang Liu, Wenyu Peng, Yun Liao, Junhui Liu

IET Image Processing

DOI

2022

Image colorization using deep convolutional auto-encoder with multi-skip connections

Xin Jin, Yide Di, Qian Jiang, Xing Chu, Qing Duan, Shao-Qing Yao, Wei Zhou

Soft Computing - A Fusion of Foundations, Methodologies and Applications

DOI

2022

Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor

Yun Liao, Yide Di, Hao Zhou, An-Ran Li, Junhui Liu, Mingyu Lu, Qing Duan

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

DOI

2021

Color-UNet++: A resolution for colorization of grayscale images using improved UNet++

Yide Di, Xiao-Ke Zhu, Xin Jin, Qiwei Dou, Wei Zhou, Qing Duan

Multimedia tools and applications

DOI

2020

基于迁移学习的家猪图像识别研究

谢碧森，段清，刘俊晖，廖赟，张逸

《软件导刊》

2003

采用形式化技术的软件再工程

周华，李少云，段清，何彦彬，沈勇

《计算机工程与应用》

段清

精选作品

期刊论文

MambaSC: A Feature Matching Method Using Mamba2 with Self and Cross-Attention for Multimodal Images

SeViMatch: A Detector-Based Image Matching Framework with Semantic-Visual Fusion

FFMatch: A FilterFormer-Based Network for Accurate Multimodal Image Matching

BiFGA: A Bidirectional Image–Text-Guided Fine-Grained Alignment Method for Remote Sensing Image–Text Retrieval

Multisemantics-Aware Optimal Feature Matching for Multimodal Remote Sensing Images

RSGM: a multi-modal image matching scheme guided by regional semantics

面向数字文化产品的虚拟现实人机交互通用路径研究与实践

基于UE5和面向微小型团队的虚拟摄制技术实践探索

UFM: Unified feature matching pre-training with multi-modal image assistants

A Survey on Neural Radiance Fields

PMCMatcher: A Parallel Multi-Scale Cascaded Transformer-Based Network for Multimodal Feature Matching

Semi-dense feature matching with increased matching amount

WinMRSI: Feature Matching With Window Attention for Multimodal Remote Sensing Image

FmCFA: a feature matching method for critical feature attention in multimodal images

MSSA: A Multi-Scale Semantic-Aware Method for Remote Sensing Image–Text Retrieval

Local feature matching from detector-based to detector-free: a survey

Using scale-equivariant CNN to enhance scale robustness in feature matching

MIVI: multi-stage feature matching for infrared and visible image

FeMIP: detector-free feature matching for multimodal images with policy gradient

SMDAF: A novel keypoint based method for copy-move forgery detection

Image colorization using deep convolutional auto-encoder with multi-skip connections

Feature Matching and Position Matching Between Optical and SAR With Local Deep Feature Descriptor

Color-UNet++: A resolution for colorization of grayscale images using improved UNet++

基于迁移学习的家猪图像识别研究

采用形式化技术的软件再工程

预印本

TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching

研究方向