方志军｜上海工程技术大学｜学者主页

2026

基于动态脑网络特征的情绪识别方法

王海玲，姜廷威，方志军，高宇飞

《计算机工程》

DOI

2026

基于模型预分配与自蒸馏的个性化联邦学习方法

张珂嘉，方志军，周南润，史志才

《计算机应用》

2026

PMG-SAM: Boosting Auto-Segmentation of SAM with Pre-Mask Guidance

Jixi Gao, Xiaoyan Jiang, Anjie Wang, Yong-Bin Gao, Zhijun Fang, Michael S. Lew

Italian National Conference on Sensors

DOI

2026

A Multi-Scale Spatially Collaborative Frequency-Guided Network for Image Deraining

Xiaoyu Zhao, Shubo Zhou, Xue-qin Jiang, Xiao-Ming Ding, Huanchun Peng, Feng Pan, Zhijun Fang

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2026

DAME-Cap: a dual-teacher and parallel attention–mambablock framework for image captioning

Kang He, Juan Zhang, Yong-Bin Gao, Zhijun Fang

Signal, Image and Video Processing

DOI

2026

Effective Range and Optimal Frequency of Through-the-Earth Magnetic Induction Communication

Hong-Guang Ma, Er-Wu Liu, Wei Ni, Jun Zhu, Zhijun Fang, Rui Wang, Yongbin Gao, Xin-Yu Qu

IEEE Transactions on Vehicular Technology

DOI

2026

Probabilistic Monocular and Multiview Network With Reliability-Aware Cost Volume Fusion for Depth Estimation

Anjie Wang, Gui-Biao Liao, Zhongyuan Zhao, Ruotong Li, Zhijun Fang, Si-Wei Ma, Jenq-Neng Hwang

IEEE Transactions on Instrumentation and Measurement

DOI

2026

Coupling Acoustic Geometry and Visual Semantics for Robust Depth Estimation

Anjie Wang, Mingxuan Chen, Xiaoyan Jiang, Yongbin Gao, Zhijun Fang, Si-Wei Ma

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2026

Dual-contextual scalable video coding for human-machine collaborative intelligence

Tengyao Cui, Yong-Fang Wang, Zhijun Fang, Yong-Qin Fang

Displays (Guildford)

DOI

2026

Towards LiDAR point cloud geometry compression using rate-distortion optimization and adaptive quantization for human-machine vision

Yi-Han Wang, Yong-Fang Wang, Shuo Zhu, Zhijun Fang

Displays (Guildford)

DOI

2026

Towards point cloud geometry compression via global-local and multi-scale feature learning

Yi-Han Wang, Yong-Fang Wang, Zhijun Fang, Tengyao Cui

Digit. Signal Process.

DOI

2025

基于可逆神经网络的点云无损编码

王楷元，方志军，卢俊鑫

《激光与光电子学进展》

2025

基于可逆神经网络的点云几何有损编码

王楷元，方志军

《无线电通信技术》

2025

Adversarial Learning Based Error Detection for Industrial Knowledge Graphs

Xun Zhu, Yuanyuan Li, Linsheng Guo, Bo Huang, Zhijun Fang

Lecture notes in computer science

DOI

2025

Continual few-shot relation extraction via multi-task balanced dual-branch network

ChenYang Shan, Juan Zhang, Zhijun Fang, Yong-Bin Gao, Bo Huang

Neurocomputing

DOI

2025

A Chinese question and answer system for liver cancer based on knowledge graph and large language mode

Haoqi Wu, Min Zhang, Hailing Wang, Xiao-Yan Jiang, Yongbin Gao, Rong-Fang Huang, Zhijun Fang, Xiaojun Hu, Yingfang Fan

Frontiers Artif. Intell.

DOI

2025

ECKT: enhancing cross-task knowledge transfer in continual few-shot relation extraction

Yifan Yao, Juan Zhang, Zhijun Fang, Yong-Bin Gao

Journal of Supercomputing

DOI

2025

Human-object interaction detection based on adaptive contrastive learning and class-specific feature enhancement

Huanchun Peng, Kejun Xue, Xincheng Wang, Yongbin Gao, Zhijun Fang, Xiao-Yan Jiang, Wenjun Yu, Chenmou Wu

Applied intelligence (Boston)

DOI

2025

Through-the-Earth Magnetic Induction Communication and Networking: A Comprehensive Survey

Hong-Guang Ma, Er-Wu Liu, Wei Ni, Zhijun Fang, Rui Wang, Yongbin Gao, D. Niyato, Ekram Hossain

IEEE Communications Surveys and Tutorials

DOI

2025

Liver cancer knowledge graph construction based on dynamic entity replacement and masking strategies RoBERTa-wwm-large-BiLSTM-CRF model with clinical Chinese EMRs

Yichi Zhang, Xiaojun Hu, Hailing Wang, Ke Liu, Yongbin Gao, Xiao-Yan Jiang, Yingfang Fan, Zhijun Fang

Frontiers Artif. Intell.

DOI

2025

Learning prototypes from background and latent objects for few-shot semantic segmentation

Yi-Cong Wang, Rong Huang, Shu-Bo Zhou, Xue-Qin Jiang, Zhijun Fang

Knowledge-Based Systems

DOI

2025

Dual flow reverse distillation for unsupervised anomaly detection

Xue-qin Jiang, Kai Huang, Shubo Zhou, Weiyu Hu, Huanchun Peng, Jiangliang Jin, Zhijun Fang

Digit. Signal Process.

DOI

2025

Enhancing lightweight image super-resolution with hybrid convolution and attention

Hanwen Shi, Shu-Bo Zhou, Yinghua Xie, Feng Pan, Zhijun Fang, Xue-qin Jiang

Pattern Recognition Letters

DOI

2025

Adaptive frequency selection network for low-light image enhancement

Shu-Bo Zhou, Jingjing Jiang, Zhijun Fang, Xiao-Ming Ding, Rong-Fang Huang, Xue-qin Jiang

Displays (Guildford)

DOI

2025

Semantic and Saliency-Aware Scalable Image Coding Toward Human–Machine Collaboration

Tengyao Cui, Yong-Fang Wang, Yi-Han Wang, Zhijun Fang

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

DOI

2025

Large-scale generative dataset, benchmark, and edge-empowered transformer for crack detection

Hao-Ran He, Yong-Fang Wang, Wei Chen, Zi-Xuan Li, Zhijun Fang

Information Sciences

DOI

2024

基于双重注意力机制增强的复合型眼震分类框架

王卓然，方志军，王海玲，高永彬，李玉霞

《中国医学物理学杂志》

2024

Adaptive multimodal prompt for human-object interaction with local feature enhanced transformer

Kejun Xue, Yongbin Gao, Zhijun Fang, Xiao-Yan Jiang, Wenjun Yu, Mingxuan Chen, Chenmou Wu

Applied intelligence (Boston)

DOI

2024

High-resolution enhanced cross-subspace fusion network for light field image superresolution

Shixu Ying, Shubo Zhou, Xue-qin Jiang, Yongbin Gao, Feng Pan, Zhijun Fang

Displays (Guildford)

DOI

2024

Enhanced side information fusion framework for sequential recommendation

Zheng-Ang Su, Juan Zhang, Zhijun Fang, Yong-Bin Gao

International Journal of Machine Learning and Cybernetics

DOI

2024

Fast-Fading Channel and Power Optimization of the Magnetic Inductive Cellular Network

Hong-Guang Ma, Erwu Liu, Zhijun Fang, Rui Wang, Yongbin Gao, Wenjun Yu, Dong-Ming Zhang

IEEE Transactions on Wireless Communications

DOI

2024

Multi-modal Scene Global Fusion Framework for Enhanced Depth Estimation

Anjie Wang, Xujun Wei, Mingxuan Chen, Xiao-Yan Jiang, Yongbin Gao, Zhijun Fang, Si-Wei Ma

International Conference on Neural Information Processing

DOI

2024

Self-Enhanced Attention for Image Captioning

Qingyun Sun, Juan Zhang, Zhijun Fang, Yong-Bin Gao

Neural Processing Letters

DOI

2024

TV-Net: A Structure-Level Feature Fusion Network Based on Tensor Voting for Road Crack Segmentation

Wenwen Zheng, Xiao-Yan Jiang, Zhijun Fang, Yongbin Gao

IEEE transactions on intelligent transportation systems (Print)

DOI

2024

Dynamic Convolution Based Intelligent Algorithm for YOLOv5 Underwater Target Detection

Jialing Jiang, Bo Huang, Zhijun Fang, Yongbin Gao

New Trends in Software Methodologies, Tools and Techniques

DOI

2024

Enhancing Few-Shot Out-of-Distribution Detection With Pre-Trained Model Features

Jiu-Qing Dong, Yifan Yao, Wei Jin, Heng Zhou, Yongbin Gao, Zhijun Fang

IEEE Transactions on Image Processing

DOI

2024

G-K BertDTA: A graph representation learning and semantic embedding-based framework for drug-target affinity prediction

Xi-He Qiu, Haoyu Wang, Xiao-Yu Tan, Zhijun Fang

Comput. Biol. Medicine

DOI

2024

Research on fabric surface defect detection algorithm based on improved Yolo_v4

Yuanyuan Li, Liyuan Song, Yin Cai, Zhijun Fang, M. Tang

Scientific Reports

DOI

2024

Occupancy map-based low complexity motion prediction for video-based point cloud compression

Yi-Han Wang, Yong-Fang Wang, Tengyao Cui, Zhijun Fang

Journal of Visual Communication and Image Representation

DOI

2024

A Multiscale Coarse-to-Fine Human Pose Estimation Network With Hard Keypoint Mining

Xiao-Yan Jiang, Hangyu Tao, Jenq-Neng Hwang, Zhijun Fang

IEEE Transactions on Systems, Man & Cybernetics. Systems

DOI

2024

A lightweight RGB superposition effect adjustment network for low-light image enhancement and denoising

Pei-Bin Chen, Juan Zhang, Yong-Bin Gao, Zhijun Fang, Jenq-Neng Hwang

Engineering applications of artificial intelligence

DOI

2024

Monocular Depth and Ego-motion Estimation with Scale Based on Superpixel and Normal Constraints

Junxin Lu, Yongbin Gao, Jie-Yu Chen, J. Hwang, Hamido Fujita, Zhijun Fang

ACM Trans. Multim. Comput. Commun. Appl.

DOI

2024

Fast Video-Based Point Cloud Compression Based on Early Termination and Transformer Model

Yi-Han Wang, Yong-Fang Wang, Tengyao Cui, Zhijun Fang

IEEE Transactions on Emerging Topics in Computational Intelligence

DOI

2023

融合空洞卷积网络的无监督单目深度恢复

齐欣宇，方志军，杨淑群

《小型微型计算机系统》

2023

基于动态物体跟踪的语义SLAM

刘家麒，高永彬，姜晓燕，方志军

《计算机应用研究》

2023

F-SCP: An automatic prompt generation method for specific classes based on visual language pre-training models

Baihong Han, Xiao-Yan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao

Pattern Recognition

DOI

2023

Depth Estimation of Multi-Modal Scene Based on Multi-Scale Modulation

Anjie Wang, Zhijun Fang, Xiao-Yan Jiang, Yong-Bin Gao, Gaofeng Cao, Si-Wei Ma

International Conference on Information Photonics

DOI

2023

Entity alignment based on informative neighbor sampling and multi-embedding graph matching

Chunmei Liu, Yong-Bin Gao, Zhijun Fang

Multimedia tools and applications

DOI

2023

Gram-based Attentive Neural Ordinary Differential Equations Network for Video Nystagmography Classification

Xi-He Qiu, Shaojie Shi, Xiao-Yu Tan, Chao Qu, Zhijun Fang, Hailing Wang, Yongbin Gao, Peixia Wu, Hua-Wei Li

IEEE International Conference on Computer Vision

DOI

2023

MFNCA: Multi-level Fusion Network Based on Cross Attention for 3D Point Cloud Object Detection

Shuo Zhu, Yong-Fang Wang, Wei Chen, Zhijun Fang

International Forum on Digital TV and Wireless Multimedia Communication

DOI

2023

Perceptual Blind Panoramic Image Quality Assessment Based on Super-Pixel

Shuyu Xiao, Yong-Fang Wang, Yin-Han Wang, Zhijun Fang

International Forum on Digital TV and Wireless Multimedia Communication

DOI

2022

端到端优化的3D点云几何信息有损压缩模型

徐嘉诚，方志军，黄勃，高永彬，周恒

《武汉大学学报(理学版)》

2022

面向形状特征的多维度多层级点云分析

徐嘉利，方志军，伍世虔

《中国图象图形学报》

2022

基于特征负反馈卷积的点云分析方法

邓林涛，方志军

《激光与光电子学进展》

2022

基于深度估计与自我运动联合优化的三维重建

田方正，高永彬，方志军，顾佳

《传感器与微系统》

2022

融合门控自校准机制和图卷积网络的点云分析

徐嘉利，方志军，伍世虔

《激光与光电子学进展》

2022

An Angular Shrinkage BERT Model for Few-Shot Relation Extraction with None-of-The-Above Detection

Junwen Wang, Yong-Bin Gao, Zhijun Fang

Social Science Research Network

DOI

2021

点线特征结合的RGB-D视觉里程计

卢俊鑫，方志军，陈婕妤，高永彬

《光学学报》

2021

RGB-D Visual Odometry Combined with Points and Lines

Jun-Xin Lu, Zhijun Fang, Jie-Yu Chen, Yong-Bin Gao

DOI

2020

基于深度学习的冠状动脉CTA三维分割

刘敏，方志军，高永彬

《智能计算机与应用》

2020

3D object detection based on domain attention and dilated convolution

Juan Yan, Zhijun Fang, Yongbin Gao

Journal of Image and Graphics

DOI

2019

多阶段冠状动脉CTA三维分割算法

刘敏，方志军，高永彬

《信号处理》

DOI

2017

基于深度学习的人体图像分割算法

王鹏，方志军，赵晓丽，黄勃，Hwang Jenq-Neng

《武汉大学学报(理学版)》

2017

基于数据中心功率特性的微电网稳压效果研究

黄宇丹，曾国辉，鲁敦科，方志军，黄勃

《电子科技》

2011

Interpolation-Based Direction-Adaptive Lifting DWT and Modified SPIHT for Image Compression in Multimedia Communications

Zhijun Fang, Naixue Xiong, Laurence T. Yang, Xingming Sun, Yan Yang

Ieee Systems Journal，Vol. 50, No. 40

DOI

2011

A Fingerprint Recognition Scheme Based on Assembling Invariant Moments for Cloud Computing Communications

Jucheng Yang, Naixue Xiong, Athanasios V. Vasilakos, Zhijun Fang, Dongsun Park, Xianghua Xu, Sook Yoon, Shanjuan Xie, Yong Yang

Ieee Systems Journal，Vol. 50, No. 40

DOI

2009

基于运动控制卡的多工位数控冲床控制系统的研究与应用

王立朝，谷安，张新朋，方志军

《机电一体化》

2009

基于触须传感器的移动机器人控制研究

方志军

《南京航空航天大学》

精选作品

期刊论文

基于动态脑网络特征的情绪识别方法

基于模型预分配与自蒸馏的个性化联邦学习方法

PMG-SAM: Boosting Auto-Segmentation of SAM with Pre-Mask Guidance

A Multi-Scale Spatially Collaborative Frequency-Guided Network for Image Deraining

DAME-Cap: a dual-teacher and parallel attention–mambablock framework for image captioning

Effective Range and Optimal Frequency of Through-the-Earth Magnetic Induction Communication

Probabilistic Monocular and Multiview Network With Reliability-Aware Cost Volume Fusion for Depth Estimation

Coupling Acoustic Geometry and Visual Semantics for Robust Depth Estimation

Dual-contextual scalable video coding for human-machine collaborative intelligence

Towards LiDAR point cloud geometry compression using rate-distortion optimization and adaptive quantization for human-machine vision

Towards point cloud geometry compression via global-local and multi-scale feature learning

基于可逆神经网络的点云无损编码

基于可逆神经网络的点云几何有损编码

Adversarial Learning Based Error Detection for Industrial Knowledge Graphs

Continual few-shot relation extraction via multi-task balanced dual-branch network

A Chinese question and answer system for liver cancer based on knowledge graph and large language mode

ECKT: enhancing cross-task knowledge transfer in continual few-shot relation extraction

Human-object interaction detection based on adaptive contrastive learning and class-specific feature enhancement

Through-the-Earth Magnetic Induction Communication and Networking: A Comprehensive Survey

Liver cancer knowledge graph construction based on dynamic entity replacement and masking strategies RoBERTa-wwm-large-BiLSTM-CRF model with clinical Chinese EMRs

Learning prototypes from background and latent objects for few-shot semantic segmentation

Dual flow reverse distillation for unsupervised anomaly detection

Enhancing lightweight image super-resolution with hybrid convolution and attention

Adaptive frequency selection network for low-light image enhancement

Semantic and Saliency-Aware Scalable Image Coding Toward Human–Machine Collaboration

Large-scale generative dataset, benchmark, and edge-empowered transformer for crack detection

基于双重注意力机制增强的复合型眼震分类框架

Adaptive multimodal prompt for human-object interaction with local feature enhanced transformer

High-resolution enhanced cross-subspace fusion network for light field image superresolution

Enhanced side information fusion framework for sequential recommendation

Fast-Fading Channel and Power Optimization of the Magnetic Inductive Cellular Network

Multi-modal Scene Global Fusion Framework for Enhanced Depth Estimation

Self-Enhanced Attention for Image Captioning

TV-Net: A Structure-Level Feature Fusion Network Based on Tensor Voting for Road Crack Segmentation

Dynamic Convolution Based Intelligent Algorithm for YOLOv5 Underwater Target Detection

Enhancing Few-Shot Out-of-Distribution Detection With Pre-Trained Model Features

G-K BertDTA: A graph representation learning and semantic embedding-based framework for drug-target affinity prediction

Research on fabric surface defect detection algorithm based on improved Yolo_v4

Occupancy map-based low complexity motion prediction for video-based point cloud compression

A Multiscale Coarse-to-Fine Human Pose Estimation Network With Hard Keypoint Mining

A lightweight RGB superposition effect adjustment network for low-light image enhancement and denoising

Monocular Depth and Ego-motion Estimation with Scale Based on Superpixel and Normal Constraints

Fast Video-Based Point Cloud Compression Based on Early Termination and Transformer Model

融合空洞卷积网络的无监督单目深度恢复

基于动态物体跟踪的语义SLAM

F-SCP: An automatic prompt generation method for specific classes based on visual language pre-training models

Depth Estimation of Multi-Modal Scene Based on Multi-Scale Modulation

Entity alignment based on informative neighbor sampling and multi-embedding graph matching

Gram-based Attentive Neural Ordinary Differential Equations Network for Video Nystagmography Classification

MFNCA: Multi-level Fusion Network Based on Cross Attention for 3D Point Cloud Object Detection

Perceptual Blind Panoramic Image Quality Assessment Based on Super-Pixel

端到端优化的3D点云几何信息有损压缩模型

面向形状特征的多维度多层级点云分析

基于特征负反馈卷积的点云分析方法

基于深度估计与自我运动联合优化的三维重建

融合门控自校准机制和图卷积网络的点云分析

An Angular Shrinkage BERT Model for Few-Shot Relation Extraction with None-of-The-Above Detection

点线特征结合的RGB-D视觉里程计

推荐系统研究进展与应用

RGB-D Visual Odometry Combined with Points and Lines

基于深度学习的冠状动脉CTA三维分割

3D object detection based on domain attention and dilated convolution

多阶段冠状动脉CTA三维分割算法

基于深度学习的人体图像分割算法

基于数据中心功率特性的微电网稳压效果研究

Interpolation-Based Direction-Adaptive Lifting DWT and Modified SPIHT for Image Compression in Multimedia Communications

A Fingerprint Recognition Scheme Based on Assembling Invariant Moments for Cloud Computing Communications

基于运动控制卡的多工位数控冲床控制系统的研究与应用

基于触须传感器的移动机器人控制研究

会议论文

基于DCT帧间变换的分级编码研究