孔军｜江南大学｜学者主页

2026

基于时频域注意力与局部归一化损失的时间序列异常检测

李佑猛，孔军，蒋敏

《计算机应用研究》

2026

From noise to structure: structured semantic reconstruction for text-based person retrieval

Jie Chen, Xi Luo, Jun Kong, Min Jiang

International Journal of Machine Learning and Cybernetics

DOI

2026

WaveRID: wavelet representation for infrared-visible person re-identification

Junyang Lai, Xuefeng Tao, Jun Kong

International Journal of Machine Learning and Cybernetics

DOI

2026

Hierarchical Concept Alignment Meets Counterfactual Invariance for Semantic-Faithful Person Retrieval

Jiayi Li, Min Jiang, Jun Kong, Xuefeng Tao, Ajmal Saeed Mian

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2026

Confidence-Guided Latent Chain-of-Thought Reasoning for Text-Based Person Retrieval

J S Chen, Min Jiang, Jun Kong, X H Luo

IEEE Signal Processing Letters

DOI

2025

基于时空协同滤波的事件行人重识别

陈万章，孔军

《计算机应用研究》

2025

基于异构鉴别器的多源图像融合方法

黄雅玲，孔军，陶雪峰

《信息与电脑》

2025

多任务联合的雾天多源图像融合方法研究

黄雅玲，孔军

《信息记录材料》

DOI

2025

Hierarchical semantic compactness and proxy sparsity learning with event inversion for event person re-identification

Wanzhang Chen, Jun Kong, Min Jiang, Xuefeng Tao

Journal of Electronic Imaging

DOI

2024

基于伪标签的无监督电力数据异常检测框架

林卫伟，白向阳，孔军

《计算机仿真》

2024

MIAFusion: Infrared and Visible Image Fusion via Multi-scale Spatial and Channel-Aware Interaction Attention

Teng Lin, Ming Lu, Min Jiang, Jun Kong

Lecture notes in computer science

DOI

2024

MIRFuse: an infrared and visible image fusion model based on disentanglement representation via mutual information regularization

Shiliang Zhou, Jun Kong, Min Jiang, Danfeng Zhuang

Journal of Electronic Imaging

DOI

2024

SMFD: an end-to-end infrared and visible image fusion model based on shared-individual multi-scale feature decomposition

Mingrui Xu, Jun Kong, Min Jiang, Tianshan Liu

Journal of Applied Remote Sensing

DOI

2024

MCFusion: infrared and visible image fusion based multiscale receptive field and cross-modal enhanced attention mechanism

Min Jiang, Zhiyuan Wang, Jun Kong, Danfeng Zhuang

Journal of Electronic Imaging

DOI

2023

Motion information supplement for joint detection and embedding tracking

Ensen Mo, Jun Kong, Min Jiang, Tianshan Liu

Journal of Electronic Imaging

DOI

2023

Multiformer-based hybrid learning with outlier re-assignment for unsupervised person re-identification

Min Jiang, Qian Zhang, Jun Kong

International Journal of Machine Learning and Cybernetics

DOI

2023

Distilling Privileged Knowledge for Anomalous Event Detection From Weakly Labeled Videos

Tianshan Liu, Kin‐Man Lam, Jun Kong

IEEE Transactions on Neural Networks and Learning Systems

DOI

2023

Feature difference and feature correlation learning mechanism for skeleton-based action recognition

Ruxin Qing, Min Jiang, Jun Kong

Journal of Electronic Imaging

DOI

2022

Dynamic trajectory quantification strategy for multiple object tracking with feature rearrangement

Yuanshu Zhang, Qing Tian, Tianshan Liu, Jun Kong

Journal of Electronic Imaging

DOI

2022

Mini-transformer with pooling for unsupervised domain adaptation person reidentification

Лей Ма，Min Jiang，Jun Kong

Journal of Electronic Imaging

DOI

2022

Selective relation-aware representations for person re-identification

X. L. Luo, Min Jiang, Jun Kong

International Journal of Machine Learning and Cybernetics

DOI

2022

Joint attentive adaptive feature fusion network for action recognition

Fan Xia, Min Jiang, Jun Kong, Danfeng Zhuang

Journal of Electronic Imaging

DOI

2022

AOH: Online Multiple Object Tracking With Adaptive Occlusion Handling

Min Jiang, Chen Zhou, Jun Kong

IEEE Signal Processing Letters

DOI

2021

基于深度残差卷积神经网络的入侵检测系统设计与实现

孔军

《合肥工业大学》

2021

基于粒子群优化的图像分割方法

孙佳雷，孔军

《信息技术与信息化》

2021

Multi-stream mixed graph convolutional networks for skeleton-based action recognition

Boyuan Zhuang, Jun Kong, Min Jiang, Tianshan Liu

Journal of Electronic Imaging

DOI

2021

Multi-views reinforced LSTM for video-based action recognition

Zhenzhen Mao, Min Jiang, Jun Kong

Journal of Electronic Imaging

DOI

2021

A novel deep learning model DDU-net using edge features to enhance brain tumor segmentation on MR images

Min Jiang, Fuhao Zhai, Jun Kong

Artificial Intelligence in Medicine

DOI

2021

Sparse Attention Module for optimizing semantic segmentation performance combined with a multi-task feature extraction network

Min Jiang, Fuhao Zhai, Jun Kong

The Visual Computer

DOI

2021

Global-locally reinforced feature extraction for person re-identification

Handan Wang, Min Jiang, Jun Kong

Journal of Electronic Imaging

DOI

2021

Diverse Features Fusion Network for video-based action recognition

Haoyang Deng, Jun Kong, Min Jiang, Tianshan Liu

Journal of Visual Communication and Image Representation

DOI

2021

Interactive information module for person re-identification

Xudong Liu, Jun Kong, Min Jiang, Sha Li

Journal of Visual Communication and Image Representation

DOI

2021

Dynamic Center Aggregation Loss With Mixed Modality for Visible-Infrared Person Re-Identification

Jun Kong, Qibin He, Min Jiang, Tianshan Liu

IEEE Signal Processing Letters

DOI

2020

基于改进神经网络的混合特征数据聚类算法

孔军

《长春大学学报》

2020

Paralleled attention modules and adaptive focal loss for Siamese visual tracking

Yuyao Zhao, Min Jiang, Jun Kong, Sha Li

IET Image Processing

DOI

2020

Spatiotemporal attention enhanced features fusion network for action recognition

Danfeng Zhuang, Min Jiang, Jun Kong, Tianshan Liu

International Journal of Machine Learning and Cybernetics

DOI

2020

Multiple depth-levels features fusion enhanced network for action recognition

Shengquan Wang, Jun Kong, Min Jiang, Tianshan Liu

Journal of Visual Communication and Image Representation

DOI

2020

Spatial-temporal saliency action mask attention network for action recognition

Min Jiang, Na Pan, Jun Kong

Journal of Visual Communication and Image Representation

DOI

2020

Visual object tracking via precise localization

Xiaodong Liu, Min Jiang, Jun Kong

Journal of Electronic Imaging

DOI

2020

Cross-level reinforced attention network for person re-identification

Min Jiang, Cong Li, Jun Kong, Zhende Teng, Danfeng Zhuang

Journal of Visual Communication and Image Representation

DOI

2020

Collaborative model tracking with robust occlusion handling

Jun Kong, Yitao Ding, Min Jiang, Sha Li

IET Image Processing

DOI

2020

Video-based person re-identification with parallel spatial–temporal attention module

Jun Kong, Zhende Teng, Min Jiang, Hongtao Huo

Journal of Electronic Imaging

DOI

2020

Multi-complement feature network for infrared-visible cross-modality person re-identification

Jun Kong, Xudong Liu, Min Jiang

Journal of Electronic Imaging

DOI

2019

高性能网络安全告警信息的关联分析方法

付泽强，王晓锋，孔军

《计算机科学》

2019

A Novel Image Segmentation Method Based on Improved Intuitionistic Fuzzy C-Means Clustering Algorithm

Jun Kong, Jian Hou, Min Jiang, Jinhua Sun

KSII Transactions on Internet and Information Systems

DOI

2019

Robust part‐based visual tracking via adaptive collaborative modelling

Jun Kong, Benxuan Wang, Min Jiang

IET Image Processing

DOI

2019

RGB-D action recognition based on discriminative common structure learning model

Tianshan Liu, Jun Kong, Min Jiang, Hongtao Huo

Journal of Electronic Imaging

DOI

2019

Collaborative multimodal feature learning for RGB-D action recognition

Jun Kong, Tianshan Liu, Min Jiang

Journal of Visual Communication and Image Representation

DOI

2019

Adaptive Weight Collaborative Complementary Learning for Robust Visual Tracking

Benxuan Wang, Jun Kong, Min Jiang, Jianyu Shen, Tianshan Liu, Xiaofeng Gu

KSII Transactions on Internet and Information Systems

DOI

2019

A Novel Text Sample Selection Model for Scene Text Detection via Bootstrap Learning

Jun Kong, Jinhua Sun, Min Jiang, Jian Hou

KSII Transactions on Internet and Information Systems

DOI

2018

基于支持向量机的输变电工程造价预测模型研究

孔军，曹小宇，肖峰

《现代电子技术》

2018

Adaptive Image Edge Detection Model Using Improved Canny Algorithm

Jun Kong, Jian Hou, Tianshan Liu, Min Jiang

IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)

DOI

2018

Human action recognition using depth motion maps pyramid and discriminative collaborative representation classifier

Jun Kong, 昝宝锋 Zan Baofeng, Min Jiang

Journal of Electronic Imaging

DOI

2018

Face Recognition Based on CSGF(2D)2PCANet

Jun Kong, Min Chen, Min Jiang, Jinhua Sun, Jian Hou

IEEE Access

DOI

2017

Collaborative model with adaptive selection scheme for visual tracking

Tianshan Liu, Jun Kong, Min Jiang, Chenhua Liu, Xiaofeng Gu, Xiaofeng Wang

International Journal of Machine Learning and Cybernetics

DOI

2017

Robust visual tracking based on kernelized correlation filters

Min Jiang, Jianyu Shen, Jun Kong, Benxuan Wang

IEEE International Conference on Information and Automation (ICIA)

DOI

2017

Action recognition using vague division DMMs

Ke Jin, Min Jiang, Jun Kong, Hongtao Huo, Xiaofeng Wang

The Journal of Engineering

DOI

2017

Convolutional Neural Networks for Water Body Extraction from Landsat Imagery

Long Yu, Zhiyin Wang, Shengwei Tian, Feiyue Ye, Jianli Ding, Jun Kong

International Journal of Computational Intelligence and Applications

DOI

2017

GB(2D)2 PCA-based convolutional network for face recognition

Min Jiang, Ruru Lu, Jun Kong, Xiao‐Jun Wu, Hongtao Huo, Xiaofeng Wang

Journal of Electronic Imaging

DOI

2017

A New Blind Deblurring Method via Hyper-laplacian Prior

Jun Kong, Kesai Lu, Min Jiang

Procedia Computer Science

DOI

2017

New Approach for Image Segmentation Based on Graph Cuts

Jun Kong, Kun Gao, Min Jiang, Chenhua Liu, Yan Li

International Journal of Signal Processing Image Processing and Pattern Recognition

DOI

2016

基于时空模型的尺度自适应跟踪算法

蒋敏，吴佼，孔军，柳晨华

《小型微型计算机系统》

2016

基于缺陷模式匹配的静态源码分析技术研究

孔军，吴伟明，谷勇浩

《软件》

2016

Generalized ℓP-regularized representation for visual tracking

Jun Kong, Chenhua Liu, Min Jiang, Jiao Wu, Shengwei Tian, Huicheng Lai

Neurocomputing

DOI

2015

一种面向高斯差分图的压缩感知目标跟踪算法

孔军，蒋敏，唐晓微，孙怡宁，姜克，温广瑞

《红外与毫米波学报》

2015

A space-based infrared image detection algorithm of background rigid motion

Yan Li, Zheng Li, Xinyi Tang, Jun Kong

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE

DOI

2015

Informative joints based human action recognition using skeleton contexts

Min Jiang, Jun Kong, George N. Bebis, Hongtao Huo

Signal Processing Image Communication

DOI

2014

改进Elman神经网络在氧化还原电位预测中的应用

蔡鑫，南新元，孔军

《安徽大学学报(自然科学版)》

2014

多尺度空间特征提取的脊柱图像拼接算法

唐晓微，孔军，蒋敏，张琳琳

《计算机工程与应用》

2014

3D Gaussian bin based sparse representation for action recognition

Min Jiang, Jun Kong, Yining Sun

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE

DOI

2014

IR remote sensing image registration based on multi-scale feature extraction

Jun Kong, Min Jiang, Jun Kong, Jun Kong, Yining Sun

DOI

2011

基于多尺度特征提取的均值漂移目标跟踪算法

孔军，汤心溢，蒋敏，葛运建

《计算机工程》

2011

基于多尺度特征提取的运动目标定位研究

孔军，汤心溢，蒋敏

《红外与毫米波学报》

2011

基于多尺度特征提取的Kalman滤波跟踪

孔军，汤心溢，蒋敏，刘士建，李丹

《红外与毫米波学报》

2010

多尺度特征提取的双目视觉匹配

孔军，汤心溢，蒋敏

《计算机工程与应用》

2007

基于UML时序图的网络视频监控系统

孔军，蒋敏

《电子技术》

2005

基于Socket的多平台通讯研究

蒋敏，单家芳，孔军

《计算机工程与应用》

2003

基于IP多播的桌面视频会议系统

章军，朱迎江，孔军，马祖长，孙怡宁

《电子技术》

精选作品

期刊论文

基于时频域注意力与局部归一化损失的时间序列异常检测

From noise to structure: structured semantic reconstruction for text-based person retrieval

WaveRID: wavelet representation for infrared-visible person re-identification

Hierarchical Concept Alignment Meets Counterfactual Invariance for Semantic-Faithful Person Retrieval

Confidence-Guided Latent Chain-of-Thought Reasoning for Text-Based Person Retrieval

基于时空协同滤波的事件行人重识别

基于异构鉴别器的多源图像融合方法

多任务联合的雾天多源图像融合方法研究

Hierarchical semantic compactness and proxy sparsity learning with event inversion for event person re-identification

基于伪标签的无监督电力数据异常检测框架

MIAFusion: Infrared and Visible Image Fusion via Multi-scale Spatial and Channel-Aware Interaction Attention

MIRFuse: an infrared and visible image fusion model based on disentanglement representation via mutual information regularization

SMFD: an end-to-end infrared and visible image fusion model based on shared-individual multi-scale feature decomposition

MCFusion: infrared and visible image fusion based multiscale receptive field and cross-modal enhanced attention mechanism

Motion information supplement for joint detection and embedding tracking

Multiformer-based hybrid learning with outlier re-assignment for unsupervised person re-identification

Distilling Privileged Knowledge for Anomalous Event Detection From Weakly Labeled Videos

Feature difference and feature correlation learning mechanism for skeleton-based action recognition

Dynamic trajectory quantification strategy for multiple object tracking with feature rearrangement

Mini-transformer with pooling for unsupervised domain adaptation person reidentification

Selective relation-aware representations for person re-identification

Joint attentive adaptive feature fusion network for action recognition

AOH: Online Multiple Object Tracking With Adaptive Occlusion Handling

基于深度残差卷积神经网络的入侵检测系统设计与实现

基于粒子群优化的图像分割方法

Multi-stream mixed graph convolutional networks for skeleton-based action recognition

Multi-views reinforced LSTM for video-based action recognition

A novel deep learning model DDU-net using edge features to enhance brain tumor segmentation on MR images

Sparse Attention Module for optimizing semantic segmentation performance combined with a multi-task feature extraction network

Global-locally reinforced feature extraction for person re-identification

Diverse Features Fusion Network for video-based action recognition

Interactive information module for person re-identification

Dynamic Center Aggregation Loss With Mixed Modality for Visible-Infrared Person Re-Identification

基于改进神经网络的混合特征数据聚类算法

Paralleled attention modules and adaptive focal loss for Siamese visual tracking

Spatiotemporal attention enhanced features fusion network for action recognition

Multiple depth-levels features fusion enhanced network for action recognition

Spatial-temporal saliency action mask attention network for action recognition

Visual object tracking via precise localization

Cross-level reinforced attention network for person re-identification

Collaborative model tracking with robust occlusion handling

Video-based person re-identification with parallel spatial–temporal attention module

Multi-complement feature network for infrared-visible cross-modality person re-identification

高性能网络安全告警信息的关联分析方法

A Novel Image Segmentation Method Based on Improved Intuitionistic Fuzzy C-Means Clustering Algorithm

Robust part‐based visual tracking via adaptive collaborative modelling

RGB-D action recognition based on discriminative common structure learning model

Collaborative multimodal feature learning for RGB-D action recognition

Adaptive Weight Collaborative Complementary Learning for Robust Visual Tracking

A Novel Text Sample Selection Model for Scene Text Detection via Bootstrap Learning

基于支持向量机的输变电工程造价预测模型研究

Adaptive Image Edge Detection Model Using Improved Canny Algorithm

Human action recognition using depth motion maps pyramid and discriminative collaborative representation classifier

Face Recognition Based on CSGF(2D)2PCANet

Collaborative model with adaptive selection scheme for visual tracking

Robust visual tracking based on kernelized correlation filters

Action recognition using vague division DMMs

Convolutional Neural Networks for Water Body Extraction from Landsat Imagery

GB(2D)2 PCA-based convolutional network for face recognition

A New Blind Deblurring Method via Hyper-laplacian Prior

New Approach for Image Segmentation Based on Graph Cuts

基于时空模型的尺度自适应跟踪算法

基于缺陷模式匹配的静态源码分析技术研究

Generalized ℓP-regularized representation for visual tracking

一种面向高斯差分图的压缩感知目标跟踪算法

A space-based infrared image detection algorithm of background rigid motion

Informative joints based human action recognition using skeleton contexts

改进Elman神经网络在氧化还原电位预测中的应用

多尺度空间特征提取的脊柱图像拼接算法

3D Gaussian bin based sparse representation for action recognition

IR remote sensing image registration based on multi-scale feature extraction

基于多尺度特征提取的均值漂移目标跟踪算法

基于多尺度特征提取的运动目标定位研究

基于多尺度特征提取的Kalman滤波跟踪

多尺度特征提取的双目视觉匹配

基于UML时序图的网络视频监控系统

基于Socket的多平台通讯研究

基于IP多播的桌面视频会议系统