王智文｜广西科技大学｜学者主页

2026

Adaptive confidence-driven learning and cross-modal hard sample mining for unsupervised visible-infrared person re-identification

Yifeng Zhang, Canlong Zhang, Haifei Ma, Zhixin Li, Zhiwen Wang, Chunrong Wei

Information Processing & Management，Vol. 63, No. 1

DOI

2026

增加下采样分支和替换解耦头的无人机图像小目标检测算法

吕明艳，蒋联源，王智文，张灿龙

《电子器件》

2026

An edge aware low light object detection method based on an improved YOLO11n model

Qi Chen, Zhiwen Wang, Xianqin Liang, Lianyuan Jiang, Youming Chen, Xi Wang

Discover Artificial Intelligence

DOI

2026

A Lightweight Hybrid Network with Cosine Metric Classification for Fine-Grained Pet Breed Recognition

Han Kuang, Zhiwen Wang

DOI

2025

基于跨模态语义协作学习的文本行人重识别

罗赠丽，张灿龙，李志欣，王智文，韦春荣

《广西师范大学学报(自然科学版)》

DOI

2025

LwFEN:一种无监督行人再识别的轻量特征提取网络

高顺强，王智文，白云

《计算机工程与科学》

2025

基于BiFPN和注意力机制改进YOLOv5s的车辆行人检测

刘丽丽，王智文，王亮，李嘉琛，方国香，吕亦雄

《现代电子技术》

DOI

2025

面向低质图像的鲁棒对抗攻击方法研究

王智文

《电子科技大学》

2025

基于多分辨率特征定位的跨模态行人检索方法

解盛，马海菲，张灿龙，王智文，韦春荣

《广西师范大学学报(自然科学版)》

DOI

2025

多分支结构和双池化注意力机制的RetinaNet行人检测

凌以运，王智文，白云，谢世步，韦秋伶，何雨鲜

《物联网技术》

DOI

2025

基于视觉感知的智能导盲杖系统应用研究

高顺强，王智文，赵文志，李娜

《物联网技术》

DOI

2025

OVL-MAP: An Online Visual Language Map Approach for Vision-and-Language Navigation in Continuous Environments

Shuhuan Wen, Ziyuan Zhang, Yu-Xiang Sun, Zhiwen Wang

IEEE Robotics and Automation Letters

DOI

2025

YOLO-PDC: algorithm for aluminum surface defect detection based on multiscale enhanced model of YOLOv7

Na Li, Zhiwen Wang, Runxing Zhao, Kaiqi Yang, Rongyi Ouyang

Journal of Real-Time Image Processing

DOI

2025

Max–Min Pooling and Squeeze Excitation Lightweight Bidirectional Mamba for image classification

Senlin Chi, Zhiwen Wang, Lianyuan Jang, Mengsi Gong

Engineering Applications of Artificial Intelligence

DOI

2025

Dynamic feature projection and grouped contrastive learning for text-to-image person re-identification

Shun He, Canlong Zhang, Xiaochun Lu, Zhixin Li, Zhiwen Wang

Knowledge-Based Systems

DOI

2025

CMAG: Cross-Modal Attention and Graph-Enhanced Memory for Unsupervised Visible-Infrared Person Re-Identification

Yifeng Zhang, Canlong Zhang, Jun-Wei Tian, Haifei Ma, Zhixin Li, Zhiwen Wang

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2025

Multi-scale Feature Refinement via Perspective Scaling and Adaptive Regularization for text-based person search

Sheng Xie, Canlong Zhang, Runcong Ma, Zhixin Li, Zhiwen Wang, Chunrong Wei

Engineering Applications of Artificial Intelligence

DOI

2025

GKC-Net: Gated KAN with Channel-Position Attention Mechanism for Image Deraining

Mengsi Gong, Jilin Yu, Zhiwen Wang, Senlin Chi

Pattern Recognition

DOI

2025

Multi-object tracking in surveillance scenarios based on joint detection and multi-feature fusion

Runxing Zhao, Jianxin Gong, Zhiwen Wang

The Journal of Supercomputing

DOI

2025

Prototypical Graph Alignment for Text-based Person Search

Yu Huang, Canlong Zhang, Zhixin Li, Zhiwen Wang, Chunrong Wei

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2025

Recursively learning fine-grained spatial–temporal features for video-based person Re-identification

Haifei Ma, Canlong Zhang, Zhixin Li, Zhiwen Wang

Engineering Applications of Artificial Intelligence

DOI

2025

Joint feature augmentation and posture label for cloth-changing person re-identification

Liman Jiang, Canlong Zhang, Lei Wu, Zhixin Li, Zhiwen Wang, Chunrong Wei

Multimedia Systems

DOI

2024

Full-view salient feature mining and alignment for text-based person search

Sheng Xie, Canlong Zhang, Enhao Ning, Zhixin Li, Zhiwen Wang, Chunrong Wei

Expert Systems With Applications，Vol. 251

DOI

2024

YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法

郭艳，王智文，赵润星

《电子学报》

2024

复杂环境下施工场所基于YOLOv7-hat安全帽佩戴检测

郭鑫，王智文，白云，赵文志

《物联网技术》

2024

Vision-and-language navigation based on history-aware cross-modal feature fusion in indoor environment

Shu-Huan Wen, Simeng Gong, Ziyuan Zhang, F. Yu, Zhiwen Wang

Knowledge-Based Systems

DOI

2024

CCBA-NMS-YD: A Vehicle Pedestrian Detection and Tracking Method Based on Improved YOLOv7 and DeepSort

Zhenhao Yuan, Zhiwen Wang, Ruonan Zhang

World Electric Vehicle Journal

DOI

2024

Pedestrian Re-Identification Based on Weakly Supervised Multi-Feature Fusion

Changming Qin, Zhiwen Wang, Linghui Zhang, Qichang Peng, Guixing Lin, Guanlin Lu

Algorithms

DOI

2024

Person Re-identification utilizing Text to Search Video

Shunkai Zhou, Canlong Zhang, Zhixin Li, Zhiwen Wang, Chunrong Wei

IEEE International Conference on Multimedia and Expo (ICME)

DOI

2024

Mask-guided Salient Feature Mining for Cloth-Changing Person Re-identification

Liman Jiang, Canlong Zhang, Lei Wu, Zhixin Li, Zhiwen Wang, Chunrong Wei

IEEE International Conference on Multimedia and Expo (ICME)

DOI

2024

Detection of pneumonia in chest X‐ray image based on separable convolutional neural network

Gongkun Luo, Zhiwen Wang, Yuhang Wang, K. Wang

Concurrency and Computation Practice and Experience

DOI

2024

Text-based person search by non-saliency enhancing and dynamic label smoothing

Yonghua Pang, Canlong Zhang, Zhixin Li, Chunrong Wei, Zhiwen Wang

Neural Computing and Applications

DOI

2024

Gradually Spatio-Temporal Feature Activation for Target Tracking

Yanfang Deng, Canlong Zhang, Zhixin Li, Chunrong Wei, Zhiwen Wang, Shuqi Pan

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2024

Target-Aware Tracking With Spatial-Temporal Context Attention

Kaijie He, Canlong Zhang, Sheng Xie, Zhixin Li, Zhiwen Wang, Rui-Guo Qin

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2023

Multi-scene image enhancement based on multi-channel illumination estimation

Runxing Zhao, Zhiwen Wang, Wuyuan Guo, Canlong Zhang

Expert Systems With Applications，Vol. 226

DOI

2023

Discriminative feature mining with relation regularization for person re-identification

Jing Yang, Canlong Zhang, Zhixin Li, Yanping Tang, Zhiwen Wang

Information Processing & Management，Vol. 60, No. 3

DOI

2023

立定跳远腾空展体特征提取算法的研究

赵文志，王智文，郭鑫

《电脑知识与技术》

2023

Pedestrian detection using RetinaNet with multi-branch structure and double pooling attention mechanism

Lincai Huang, Zhiwen Wang, Xiaobiao Fu

Multimedia Tools and Applications

DOI

2023

SATNet: Captioning with Semantic Alignment and Feature Enhancement

Wenhui Bai, Canlong Zhang, Zhixin Li, Peiyi Wei, Zhiwen Wang

Lecture notes in computer science

DOI

2022

体现用户意图和风格的图像描述生成

王宇航，张灿龙，李志欣，王智文

《广西师范大学学报(自然科学版)》

2022

手势图像边缘检测——基于多方向和最佳阈值的Canny算法

黄林彩，王智文，符晓彪，刘美珍

《广西科技大学学报》

2022

基于改进U-Net网络的肺部CT图像结节分割方法

龙雪，李政林，王智文，呼和乌拉

《广西科技大学学报》

2022

基于改进CRNN算法的电动自行车车牌识别研究

吴静，王智文，王康权，孙金芳

《广西科技大学学报》

2022

Pedestrian detection based on multi-scale feature fusion

Lincai Huang, Zhiwen Wang, Xiaobiao Fu

IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)

DOI

2022

Pedestrian detection method based on feature fusion Centernet

Xiaobiao Fu, Zhiwen Wang, Lincai Huang, Yuhang Wang, Canlong Zhang

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

DOI

2022

Graph Structure Guided Transformer for Semantic Segmentation

Luyang Qian, Canlong Zhang, Zhixin Li, Zhiwen Wang

Proceedings - International Conference on Tools with Artificial Intelligence, TAI

DOI

2022

Image Captioning According to User's Intention and Style

Yuhang Wang, Canlong Zhang, Zhiwen Wang, Zhixin Li

2022 International Joint Conference on Neural Networks (IJCNN)

DOI

2022

Pedestrian detection in infrared image based on depth transfer learning

Zhiwen Wang, Jing Feng, Yifeng Zhang

Multimedia Tools and Applications

DOI

2021

基于多层级视觉融合的图像描述模型

周东明，张灿龙，李志欣，王智文

《电子学报》

2021

一种用于行人再辨识的批次分块遮挡网络

张灿龙，常松雨，李志欣，王智文

《小型微型计算机系统》

2021

一种改进的雾天图像增强算法

吕东，王萍，王宇航，王智文，张灿龙，潘绍明

《现代电子技术》

DOI

2021

基于关联帧差分法的运动目标检测与跟踪

王智文，王宇航，蒋联源，张灿龙，欧阳浩，黄镇谨

《现代电子技术》

DOI

2021

固体金属垃圾分类中基于深度学习方法的研究

吕东，王萍，王宇航，王智文，张灿龙

《广西科技大学学报》

DOI

2021

Pedestrian Detection Algorithm in SSD Infrared Image Based on Transfer Learning

Jing Feng, Zhiwen Wang

Communications in computer and information science

DOI

2021

Edge Detection of Agricultural Products Based on Morphologically Improved Canny Algorithm

Xiaokang Yu, Zhiwen Wang, Yuhang Wang, Canlong Zhang

Mathematical Problems in Engineering

DOI

2021

Low illumination color image enhancement based on Gabor filtering and Retinex theory

Ping Wang, Zhiwen Wang, Dong Lv, Chanlong Zhang, Yuhang Wang

Multimedia Tools and Applications

DOI

2020

Low Illumination Color Image Enhancement Based on Improved Retinex Theory

Ping Wang, Zhiwen Wang, Dong Lv, Canlong Zhang, Yuhang Wang

International Conference on Electronic Information Technology and Computer Engineering (EITCE)

DOI

2020

Multi-level Visual Fusion Networks for Image Captioning

Dongming Zhou, Canlong Zhang, Zhixin Li, Zhiwen Wang

DOI

2019

Attention and Multi-layer Fusion for Real-time Semantic Segmentation

Qinghe Cheng, Canlong Zhang, Zhixin Li, Zhiwen Wang

International Symposium on Computational Intelligence and Design

DOI

2019

Sparse High-Level Attention Networks for Person Re-Identification

Sheng Quan Xie, Canlong Zhang, Zhixin Li, Zhiwen Wang

Proceedings - International Conference on Tools with Artificial Intelligence, TAI

DOI

2019

Flower Recognition Based on Transfer Learning and Adam Deep Learning Optimization Algorithm

Jing Feng, Zhiwen Wang, Min Zha, Xinliang Cao

International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)

DOI

2019

Joint spatiograms for multi-modality tracking with online update

Can-Long Zhang, Yanping Tang, Zhixin Li, Zhiwen Wang

Pattern Recognition Letters

DOI

2019

Characteristics Extraction of Behavior of Multiplayers in Video Football Game

Zhiwen Wang, Hao Ouyang, Canlong Zhang, Bowen Tang, HU Zheng-huan, Xinliang Cao, Jing Feng, Min Zha

Lecture notes in electrical engineering

DOI

2018

Joint compressive representation for multi-feature tracking

Canlong Zhang, Zhixin Li, Zhiwen Wang

Neurocomputing

DOI

2018

Parallel Connecting Deep and Shallow CNNs for Simultaneous Detection of Big and Small Objects

Canlong Zhang, Dongcheng He, Zhixin Li, Zhiwen Wang

Lecture notes in computer science

DOI

2017

红外可见光目标的空间直方图表示与联合跟踪

张灿龙，唐艳平，李志欣，王智文，蔡冰

《中国图象图形学报》

2017

Fast circle detection algorithm based on sampling from difference area

Lianyuan Jiang, Zhiwen Wang, Yongqiang Ye, Jianbing Jiang

Optik

DOI

2017

Spatiogram and Fuzzy Logic Based Multi-modality Fusion Tracking with Online Update

Canlong Zhang, Zhixin Li, Zhiwen Wang, Ting Han

Communications in computer and information science

DOI

2016

An image segmentation method using automatic threshold based on improved genetic selecting algorithm

Zhiwen Wang, Yuhang Wang, Lianyuan Jiang, Canlong Zhang, Pengtao Wang

Automatic Control and Computer Sciences

DOI

2014

基于多元统计模型的分形小波自适应图像去噪

王智文，李绍滋

《计算机学报》

2014

Feature Fusion Using Automatic Generated RBF Neural Network

Zhiwen Wang, Gongkun Luo

Information Technology Journal

DOI

2010

基于正交小波变换和伪彩色的遥感图像增强

王智文，李绍滋，刘美珍，周健

《计算机测量与控制》

2010

Research and implement for vehicle license plate recognition based on improved BP network

Zhiwen Wang, Shaozi Li

International Conference on Computer and Communication Technologies in Agriculture Engineering

DOI

2010

Title detection algorithm for OCR credentials image based on directional projection and divergence

Zhiwen Wang, Guoqing Xie, Shaozi Li, Zhi Liu

DOI

2010

Research for automatic recognition for vehicle based on improved BP network

Zhiwen Wang, Shaozi Li

International Conference on Computer and Communication Technologies in Agriculture Engineering

DOI

2010

Remote Sensing Image Enhancement Based on Orthogonal Wavelet Transformation Analysis and Pseudo-color Processing

Zhiwen Wang, Shaozi Li, Yanping Lv, Kaitao Yang

International Journal of Computational Intelligence Systems

DOI

2009

基于小波变换的数字图像自适应盲水印算法及实现

王智文，刘美珍，蔡启先，李道丰，谢国庆

《计算机测量与控制》

2009

Binarization Algorithm of Passport Image Based on Global Iterative Threshold and Local Analysis

Zhiwen Wang, Shaozi Li, Songzhi Su, Guoqing Xie

International Conference on Information Management, Innovation Management and Industrial Engineering (ICIII)

DOI

2008

基于小波分析和伪彩色的遥感图像增强

王智文，刘美珍，蔡启先，李道丰

《计算机工程与设计》

2006

Research for vehicle license plate recognition system based on improved BP network

Zhiwen Wang

Journal of Guangxi University of Technology

2005

图像中点、线、面特征提取

王智文，谢国庆

《广西科技大学学报》

2005

基于二维特征和Fisher准则函数车牌图像分割

白莹，谢国庆，王智文

《广西科技大学学报》

2005

Car plate image segmentation based on 2_D characteristic and Fisher function

Zhiwen Wang

精选作品

期刊论文

Adaptive confidence-driven learning and cross-modal hard sample mining for unsupervised visible-infrared person re-identification

增加下采样分支和替换解耦头的无人机图像小目标检测算法

An edge aware low light object detection method based on an improved YOLO11n model

A Lightweight Hybrid Network with Cosine Metric Classification for Fine-Grained Pet Breed Recognition

基于跨模态语义协作学习的文本行人重识别

LwFEN:一种无监督行人再识别的轻量特征提取网络

基于BiFPN和注意力机制改进YOLOv5s的车辆行人检测

面向低质图像的鲁棒对抗攻击方法研究

基于多分辨率特征定位的跨模态行人检索方法

多分支结构和双池化注意力机制的RetinaNet行人检测

基于视觉感知的智能导盲杖系统应用研究

OVL-MAP: An Online Visual Language Map Approach for Vision-and-Language Navigation in Continuous Environments

YOLO-PDC: algorithm for aluminum surface defect detection based on multiscale enhanced model of YOLOv7

Max–Min Pooling and Squeeze Excitation Lightweight Bidirectional Mamba for image classification

Dynamic feature projection and grouped contrastive learning for text-to-image person re-identification

CMAG: Cross-Modal Attention and Graph-Enhanced Memory for Unsupervised Visible-Infrared Person Re-Identification

Multi-scale Feature Refinement via Perspective Scaling and Adaptive Regularization for text-based person search

GKC-Net: Gated KAN with Channel-Position Attention Mechanism for Image Deraining

Multi-object tracking in surveillance scenarios based on joint detection and multi-feature fusion

Prototypical Graph Alignment for Text-based Person Search

Recursively learning fine-grained spatial–temporal features for video-based person Re-identification

Joint feature augmentation and posture label for cloth-changing person re-identification

Full-view salient feature mining and alignment for text-based person search

YOLO-POD：基于多维注意力机制的高精度PCB微小缺陷检测算法

复杂环境下施工场所基于YOLOv7-hat安全帽佩戴检测

Vision-and-language navigation based on history-aware cross-modal feature fusion in indoor environment

CCBA-NMS-YD: A Vehicle Pedestrian Detection and Tracking Method Based on Improved YOLOv7 and DeepSort

Pedestrian Re-Identification Based on Weakly Supervised Multi-Feature Fusion

Person Re-identification utilizing Text to Search Video

Mask-guided Salient Feature Mining for Cloth-Changing Person Re-identification

Detection of pneumonia in chest X‐ray image based on separable convolutional neural network

Text-based person search by non-saliency enhancing and dynamic label smoothing

Gradually Spatio-Temporal Feature Activation for Target Tracking

Target-Aware Tracking With Spatial-Temporal Context Attention

Multi-scene image enhancement based on multi-channel illumination estimation

Discriminative feature mining with relation regularization for person re-identification

立定跳远腾空展体特征提取算法的研究

Pedestrian detection using RetinaNet with multi-branch structure and double pooling attention mechanism

SATNet: Captioning with Semantic Alignment and Feature Enhancement

体现用户意图和风格的图像描述生成

手势图像边缘检测——基于多方向和最佳阈值的Canny算法

基于改进U-Net网络的肺部CT图像结节分割方法

基于改进CRNN算法的电动自行车车牌识别研究

Pedestrian detection based on multi-scale feature fusion

Pedestrian detection method based on feature fusion Centernet

Graph Structure Guided Transformer for Semantic Segmentation

Image Captioning According to User's Intention and Style

Pedestrian detection in infrared image based on depth transfer learning

基于多层级视觉融合的图像描述模型

一种用于行人再辨识的批次分块遮挡网络

一种改进的雾天图像增强算法

基于关联帧差分法的运动目标检测与跟踪

固体金属垃圾分类中基于深度学习方法的研究

Pedestrian Detection Algorithm in SSD Infrared Image Based on Transfer Learning

Edge Detection of Agricultural Products Based on Morphologically Improved Canny Algorithm

Low illumination color image enhancement based on Gabor filtering and Retinex theory

Low Illumination Color Image Enhancement Based on Improved Retinex Theory

Multi-level Visual Fusion Networks for Image Captioning

Attention and Multi-layer Fusion for Real-time Semantic Segmentation

Sparse High-Level Attention Networks for Person Re-Identification

Flower Recognition Based on Transfer Learning and Adam Deep Learning Optimization Algorithm

Joint spatiograms for multi-modality tracking with online update

Characteristics Extraction of Behavior of Multiplayers in Video Football Game

Joint compressive representation for multi-feature tracking

Parallel Connecting Deep and Shallow CNNs for Simultaneous Detection of Big and Small Objects

红外可见光目标的空间直方图表示与联合跟踪

Fast circle detection algorithm based on sampling from difference area

Spatiogram and Fuzzy Logic Based Multi-modality Fusion Tracking with Online Update

An image segmentation method using automatic threshold based on improved genetic selecting algorithm

基于多元统计模型的分形小波自适应图像去噪

Feature Fusion Using Automatic Generated RBF Neural Network

基于正交小波变换和伪彩色的遥感图像增强

Research and implement for vehicle license plate recognition based on improved BP network

Title detection algorithm for OCR credentials image based on directional projection and divergence

Research for automatic recognition for vehicle based on improved BP network

Remote Sensing Image Enhancement Based on Orthogonal Wavelet Transformation Analysis and Pseudo-color Processing

基于小波变换的数字图像自适应盲水印算法及实现

Binarization Algorithm of Passport Image Based on Global Iterative Threshold and Local Analysis