薛彦兵｜天津理工大学｜学者主页

2026

CrossMambaStereo: Confidence-Guided State Propagation for Stereo Matching

Hongchao Chen, Yanbing Xue, Jing Cai

Eurographics

DOI

2026

A Novel Multi-View Perception and Shrinkage Aggregation Network for Inharmonious Region Localization

Sheng-Hao Chen, Chun-Jie Ma, Yi-Bo Zhao, Meng Liu, Yanbing Xue, Zan Gao

IEEE transactions on circuits and systems for video technology (Print)

DOI

2025

基于注意力机制和特征金字塔的水下扭曲图像重建网络

王奇隆，温显斌，薛彦兵，袁立明，徐海霞，史芙蓉

《天津理工大学学报》

2025

A Collaborative Hierarchical Aggregation Network for Weakly Supervised Temporal Action Localization

Zan Gao, Xiaoyi Xu, Yibo Zhao, Chunjie Ma, Yanbing Xue, Riwei Wang

ACM Transactions on Multimedia Computing Communications and Applications

DOI

2025

CACP: Covariance-Aware Cross-Domain Prototypes for Domain Adaptive Semantic Segmentation

Yanbing Xue, Xinyu Tian, Feifei Zhang, Xianbin Wen, Zan Gao, Shengyong Chen

IEEE Transactions on Multimedia

DOI

2025

HeartOx: Efficient Multi-task Learning for Contactless Heart Rate and Blood Oxygen Estimation

Mengqi Wang, Mingyu Gu, Jing Cai, Yanbing Xue

Lecture notes in computer science

DOI

2025

Mamba-based multi-branch cost aggregation for stereo matching

Xingyuan Lu, Yanbing Xue, Lei-Da Li, Shiyin Li, Zan Gao

Applied Soft Computing

DOI

2024

基于频域注意力的水下目标检测算法研究

张天，温显斌，薛彦兵，袁立明，徐海霞，史芙蓉

《光电子·激光》

DOI

2024

X-CDNet: A real-time crosswalk detector based on YOLOX

Xingyuan Lu, Yanbing Xue, Zhigang Wang, Haixia Xu, Xianbin Wen

Journal of Visual Communication and Image Representation

DOI

2024

Segmentation and Quality Assessment of Continuous Fitness Movements Based on Vision

Zeying Li, Hongtao Chen, Jing Cai, Yanbing Xue

Lecture notes in computer science

DOI

2023

Remote Physiological Measurement With Multiscale Feature Extraction and Global Attention Module

Lin Zhao, Yanbing Xue, Zhigang Wang, Jing Cai

IEEE Transactions on Consumer Electronics

DOI

2022

跟踪状态自适应的判别式行人单目标跟踪算法研究

丁明远，蔡靖，周冕，薛彦兵，温显斌

《光电子·激光》

2022

Lightweight multi-scale convolutional neural network for real time stereo matching

Yanbing Xue, Doudou Zhang, Leida Li, Shiyin Li, Yuxin Wang

Image and Vision Computing

DOI

2021

用于实时语义分割的带孔金字塔注意力网络

尹鹏峰，薛彦兵，蔡靖，高赞

《中国科技论文》

2021

Attention Stereo Matching Network

Doudou Zhang, Jing Cai, Yanbing Xue, Zan Gao, Hua Zhang

Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition

DOI

2020

Parsing human image by fusing semantic and spatial features: A deep learning approach

Ruilin Zhao, Yanbing Xue, Jing Cai, Zan Gao

Information Processing & Management，Vol. 57, No. 6

DOI

2020

A bus passenger re-identification dataset and a deep learning baseline using triplet embedding

Junliang Guo, Yanbing Xue, Jing Cai, Zan Gao, Guangping Xu, Zhang Hua

Multimedia Tools and Applications

DOI

2020

Face Recognition for Embedded System Based on Optimized Triplet Loss Neural Network

Yubo Zhao, Cheng Yang, Yushi Wang, Jing Cai, Yanbing Xue

International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)

DOI

2019

基于残差网络的三维模型检索算法

李荫民，薛凯心，高赞，薛彦兵，徐光平，张桦

《计算机科学》

2019

局部Fisher向量编码与交叉视角二次判别分析的人头重识别

何敬霞，薛彦兵，李胜利，张桦，王志岗，高赞，徐光平

《天津理工大学学报》

2019

基于density-ORB特征的图像特征点匹配算法

芦文强，薛彦兵，李胜利，张桦，王志岗，高赞，徐光平

《天津理工大学学报》

2018

基于多级子网络和排序性Dropout机制的人脸属性识别

高淑蕾，周冕，薛彦兵，徐光平，高赞，张桦

《数据采集与处理》

2018

As‐global‐as‐possible stereo matching with adaptive smoothness prior

Peng Yao, Hua Zhang, Yanbing Xue, Shengyong Chen

IET Image Processing

DOI

2018

3D object recognition based on pairwise Multi-view Convolutional Neural Networks

Zan Gao, D.Y. Wang, Yanbing Xue, Guangping Xu, Haowei Zhang, Y.L Wang

Journal of Visual Communication and Image Representation

DOI

2018

MSCS: MeshStereo with Cross‐Scale Cost Filtering for fast stereo matching

Peng Yao, Hua Zhang, Yanbing Xue, Shengyong Chen

IET Computer Vision

DOI

2018

Semantic segmentation based on fusion of features and classifiers

Yanbing Xue, Hui-qiang Geng, Hua Zhang, Zhenshan Xue, Guangping Xu

Multimedia Tools and Applications

DOI

2018

AGO: Accelerating Global Optimization for Accurate Stereo Matching

Peng Yao, Hua Zhang, Yanbing Xue, Shengyong Chen

Lecture notes in computer science

DOI

2018

Stereo Matching Based on Density Segmentation and Non-Local Cost Aggregation

Jianning Du, Yanbing Xue, Hua Zhang, Zan Gao

Lecture notes in computer science

DOI

2017

Semantic image segmentation with fused CNN features

耿慧强，张桦，薛彦兵，周冕，徐光平，高赞

Optoelectronics Letters

2017

基于深度运动轨迹信息的人体动作描述算法

章国泰，高赞，张桦，薛彦兵，徐光平

《光电子·激光》

2017

基于代价敏感深度决策树的公交车环境人脸检测

娄康，薛彦兵，张桦，徐光平，高赞，王志岗

《计算机应用》

2017

3D human action recognition model based on image set and regularized multi-task leaning

Zan Gao, Guiping Zhang, Haowei Zhang, Yanbing Xue, Guangping Xu

Neurocomputing

DOI

2017

Segment-tree based cost aggregation for stereo matching with enhanced segmentation advantage

Peng Yao, Hua Zhang, Yanbing Xue, Mian Zhou, Guangping Xu, Zan Gao, Shengyong Chen

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2017

SPMVP: Spatial PatchMatch Stereo with Virtual Pixel Aggregation

Peng Yao, Hua Zhang, Yanbing Xue, Shengyong Chen

Lecture notes in computer science

DOI

2016

一种新的多尺度深度学习图像语义理解方法研究

蒋应锋，张桦，薛彦兵，周冕，徐光平，高赞

《光电子·激光》

2016

基于分级判断的行人检测

孙黎亚，张桦，薛彦兵，王志岗

《光电子·激光》

2016

Registration of depth maps based on IRLS-ICP-TPS

Yongqiang Liu, Hua Zhang, Yanbing Xue, Guangping Xu, Zan Gao

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

DOI

2016

A Fast 3D Retrieval Algorithm via Class-Statistic and Pair-Constraint Model

Zan Gao, Deyu Wang, Hua Zhang, Yanbing Xue, Guangping Xu

ACM International Conference on Multimedia (ACM MM)

DOI

2016

Iterative color-depth MST cost aggregation for stereo matching

Peng Yao, Hua Zhang, Yanbing Xue, Mian Zhou, Guangping Xu, Zan Gao

IEEE International Conference on Multimedia and Expo (ICME)

DOI

2016

Multi-dimensional human action recognition model based on image set and group sparisty

Zan Gao, Yanlong Zhang, Haoxiang Zhang, Yanbing Xue, Guangping Xu

Neurocomputing

DOI

2016

Reverse Testing Image Set Model Based Multi-view Human Action Recognition

Zan Gao, Yanlong Zhang, Haowei Zhang, Guangping Xu, Yanbing Xue

Lecture notes in computer science

DOI

2015

基于深度稠密时空兴趣点的人体动作描述算法

宋健明，张桦，高赞，张燕，薛彦兵，徐光平

《模式识别与人工智能》

2015

Human action recognition on depth dataset

Zan Gao, Hua Zhang, Anan A. Liu, Guangping Xu, Yanbing Xue

Neural Computing and Applications

DOI

2015

Single Face Image Super-Resolution via Multi-dictionary Bayesian Non-parametric Learning

Jingjing Wu, Hua Zhang, Yanbing Xue, Mian Zhou, Guangping Xu, Zan Gao

Lecture notes in computer science

DOI

2014

基于稀疏混合模型的粒子滤波目标跟踪算法

张潍帆，王京辉，王怀彬，薛彦兵

《天津理工大学学报》

2014

基于Kinect和金字塔特征的行为识别算法

申晓霞，张桦，高赞，徐光平，薛彦兵

《光电子·激光》

2014

基于多时空特征的人体动作识别算法

宋健明，张桦，高赞，张燕，薛彦兵，徐光平

《光电子·激光》

2014

一种基于双重分割的立体匹配算法

刘少强，张桦，徐光平，薛彦兵，高赞，宋健明

《计算机辅助设计与图形学学报》

2014

Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition

Zan Gao, Haowei Zhang, Guangping Xu, Yanbing Xue

Neurocomputing

DOI

2014

Multi-view discriminative and structured dictionary learning with group sparsity for human action recognition

Zan Gao, Haoxiang Zhang, Guangping Xu, Yanbing Xue, Alex G. Hauptmann

Signal Processing

DOI

2013

基于深度信息和RGB图像的行为识别算法

申晓霞，张桦，高赞，徐光平，薛彦兵，张哲

《模式识别与人工智能》

2013

一种鲁棒的基于深度数据的行为识别算法

申晓霞，张桦，高赞，薛彦兵，徐光平

《光电子·激光》

2013

一种鲁棒的基于在线boosting目标跟踪算法研究

沈丁成，薛彦兵，张桦，徐光平，高赞

《光电子·激光》

DOI

2013

Online Boosting Tracking with Fragmented Model

Dingcheng Shen, Hua Zhang, Yanbing Xue, Guangping Xu, Zan Gao

Lecture notes in computer science

DOI

2012

结合均值漂移与最小生成树的图像分割算法

王倩，张桦，徐光平，薛彦兵

《光电子·激光》

DOI

2012

一种MEAN SHIFT跟踪改进算法研究

李超，贺鹏，刘利平，薛彦兵

《河北省科学院学报》

2011

基于链码和快速傅里叶变换的轮廓描绘方法

牛庆肖，张桦，徐光平，薛彦兵

《光电子·激光》

DOI

2011

A fuzzy identification method of contours based on chain-code features

Qi Dong, Guangping Xu, Jing Liu, Yanbing Xue, Hua Zhang

DOI

2011

Otsu thresholding segmentation algorithm based on Markov Random Field

Qian Wang, Hua Zhang, Qi Dong, Qingxiao Niu, Guangping Xu, Yanbing Xue

International Conference on Natural Computation (ICNC)

DOI

2011

A shape contour description method based on chain code and Fast Fourier Transform

Qingxiao Niu, Hua Zhang, Jing Liu, Qian Wang, Guangping Xu, Yanbing Xue

International Conference on Natural Computation (ICNC)

DOI

2010

基于多种特征的彩色车牌定位方法研究

周东升，薛彦兵，邓文慧，张桦

《河北省科学院学报》

2010

基于改进相容函数的超分辨率图像重建

张桦，马艳杰，薛彦兵

《光电子·激光》

2010

一种单帧车牌图像的超分辨率方法

邓文慧，薛彦兵，周东升，张桦

《数智技术研究与应用》

2010

A multi-scale-based super-resolution method for face image

Simiao Zhang, Hua Zhang, Lan Zhang, Yanbing Xue

International Congress on Image and Signal Processing (CISP)

DOI

2010

Single image super resolution for license plate

Yanbing Xue, Wenhui Deng, Dongsheng Zhou, Hua Zhang

International Conference on Natural Computation (ICNC)

DOI

2010

Multi-frame image super-resolution reconstruction based on GPOF registration and L1-norm

Lan Zhang, Hua Zhang, Simiao Zhang, Yanbing Xue

International Conference on Natural Computation (ICNC)

DOI

2010

License plate locating algorithm based on multi-feature in color image

Jing Sun, Yanbing Xue

International Conference on Educational and Information Technology

DOI

2009

一种新的样本块图像修补方法

雷鸣，王春东，薛彦兵，张桦

《光电子·激光》

2009

A Novel Super-Resolution Image Reconstruction Based on MRF

MA Yan-jie, Hua Zhang, Yanbing Xue

International Congress on Image and Signal Processing (CISP)

DOI

2009

Super-Resolution Image Reconstruction Based on K-Means-Markov Network

YanJie Ma, Hua Zhang, Yanbing Xue, Simiao Zhang

International Conference on Natural Computation (ICNC)

DOI

2008

基于样本块的图像修补

薛彦兵，张桦，王法玉，雷鸣

《天津理工大学学报》

精选作品

期刊论文

CrossMambaStereo: Confidence-Guided State Propagation for Stereo Matching

A Novel Multi-View Perception and Shrinkage Aggregation Network for Inharmonious Region Localization

基于注意力机制和特征金字塔的水下扭曲图像重建网络

A Collaborative Hierarchical Aggregation Network for Weakly Supervised Temporal Action Localization

CACP: Covariance-Aware Cross-Domain Prototypes for Domain Adaptive Semantic Segmentation

HeartOx: Efficient Multi-task Learning for Contactless Heart Rate and Blood Oxygen Estimation

Mamba-based multi-branch cost aggregation for stereo matching

基于频域注意力的水下目标检测算法研究

X-CDNet: A real-time crosswalk detector based on YOLOX

Segmentation and Quality Assessment of Continuous Fitness Movements Based on Vision

Remote Physiological Measurement With Multiscale Feature Extraction and Global Attention Module

跟踪状态自适应的判别式行人单目标跟踪算法研究

Lightweight multi-scale convolutional neural network for real time stereo matching

用于实时语义分割的带孔金字塔注意力网络

Attention Stereo Matching Network

Parsing human image by fusing semantic and spatial features: A deep learning approach

A bus passenger re-identification dataset and a deep learning baseline using triplet embedding

Face Recognition for Embedded System Based on Optimized Triplet Loss Neural Network

基于残差网络的三维模型检索算法

局部Fisher向量编码与交叉视角二次判别分析的人头重识别

基于density-ORB特征的图像特征点匹配算法

基于多级子网络和排序性Dropout机制的人脸属性识别

As‐global‐as‐possible stereo matching with adaptive smoothness prior

3D object recognition based on pairwise Multi-view Convolutional Neural Networks

MSCS: MeshStereo with Cross‐Scale Cost Filtering for fast stereo matching

Semantic segmentation based on fusion of features and classifiers

AGO: Accelerating Global Optimization for Accurate Stereo Matching

Stereo Matching Based on Density Segmentation and Non-Local Cost Aggregation

Semantic image segmentation with fused CNN features

基于深度运动轨迹信息的人体动作描述算法

基于代价敏感深度决策树的公交车环境人脸检测

3D human action recognition model based on image set and regularized multi-task leaning

Segment-tree based cost aggregation for stereo matching with enhanced segmentation advantage

SPMVP: Spatial PatchMatch Stereo with Virtual Pixel Aggregation

一种新的多尺度深度学习图像语义理解方法研究

基于分级判断的行人检测

Registration of depth maps based on IRLS-ICP-TPS

A Fast 3D Retrieval Algorithm via Class-Statistic and Pair-Constraint Model

Iterative color-depth MST cost aggregation for stereo matching

Multi-dimensional human action recognition model based on image set and group sparisty

Reverse Testing Image Set Model Based Multi-view Human Action Recognition

基于深度稠密时空兴趣点的人体动作描述算法

Human action recognition on depth dataset

Single Face Image Super-Resolution via Multi-dictionary Bayesian Non-parametric Learning

基于稀疏混合模型的粒子滤波目标跟踪算法

基于Kinect和金字塔特征的行为识别算法

基于多时空特征的人体动作识别算法

一种基于双重分割的立体匹配算法

Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition

Multi-view discriminative and structured dictionary learning with group sparsity for human action recognition

基于深度信息和RGB图像的行为识别算法

一种鲁棒的基于深度数据的行为识别算法

一种鲁棒的基于在线boosting目标跟踪算法研究

Online Boosting Tracking with Fragmented Model

结合均值漂移与最小生成树的图像分割算法

一种MEAN SHIFT跟踪改进算法研究

基于链码和快速傅里叶变换的轮廓描绘方法

A fuzzy identification method of contours based on chain-code features

Otsu thresholding segmentation algorithm based on Markov Random Field

A shape contour description method based on chain code and Fast Fourier Transform

基于多种特征的彩色车牌定位方法研究

基于改进相容函数的超分辨率图像重建

一种单帧车牌图像的超分辨率方法

A multi-scale-based super-resolution method for face image

Single image super resolution for license plate

Multi-frame image super-resolution reconstruction based on GPOF registration and L1-norm

License plate locating algorithm based on multi-feature in color image

一种新的样本块图像修补方法

A Novel Super-Resolution Image Reconstruction Based on MRF

Super-Resolution Image Reconstruction Based on K-Means-Markov Network

基于样本块的图像修补

会议论文

基于Color Ratio Gradient的样本块图像修补

研究方向