陈辉｜安徽理工大学｜学者主页

2026

RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance

Yi-Ming Liu, Ben Wan, Tongxuan Liu, Ao Wang, Yu-Qing Xiong, Fan Zhang, Hui Chen, Gui-Guang Ding

2026

DINO-PCB: Two-stage vision foundation model pretraining and distillation for real-time circuit-board defect detection

Jun-Jie Ke, Lihuo He, Jing Zhang, Haiming Wang, Yuqi Ji, Hui Chen, Jie Li, Si-Chen Zhao, Gui-Guang Ding, Xin-Bo Gao

Pattern Recognition

DOI

2026

融合注意力机制的CNN-Mamba的医学图像分割方法

马瀚词，陈辉

《宁夏师范大学学报》

2026

融合注意力机制和多层次特征的结肠息肉分割方法

董坤朋，陈辉

《重庆工商大学学报(自然科学版)》

2026

基于混合局部通道注意力机制的水下光学图像目标检测算法

陈辉，王奎阳，张兆贤

《桂林电子科技大学学报》

2026

面向遥感图像的改进RT-DETR目标检测算法

陈辉，王新蕾

《电子测量技术》

2026

基于改进YOLOv7的遥感图像目标检测方法

陈辉，田博，赵永红，瞿海平，梁建虎

《兰州理工大学学报》

2026

Enhanced underwater object detection via multi-scale attention and adaptive feature fusion

Hui Chen, Yongjie Yu, Tao Fu

Multimedia Systems

DOI

2026

Enhancing underwater debris detection: a dimension-aware diffusion and progressive feature enhancement approach

Yongjie Yu, Hui Chen, Shunxiang Zhang, Bin Ge, Tao Fu

The Journal of Supercomputing

DOI

2026

Frequency-decoupled multi-scale hybrid transformer for underwater object detection

Hui Chen, Yongjie Yu, Shunxiang Zhang, Bin Ge

Image and Vision Computing

DOI

2025

DAR-Prompt: Dynamic Regulation in Prompt Tuning for Multi-Label Zero-Shot Learning

Yiwen Liang, Hui Chen, Zijia Lin, Pengzhang Liu, Jiaxing Wang, Guoxin Wang, Lin Li, Sicheng Zhao, Jun-Gong Han, Gui-Guang Ding

IEEE Transactions on Image Processing

DOI

2025

YOLOE: Real-Time Seeing Anythi

Ao Wang, Lihao Liu, Hui Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

IEEE International Conference on Computer Vision

DOI

2025

Exploiting Position Information in Convolutional Kernels for Structural Re-parameterization

Tianxiang Hao, Hui Chen, Gui-Guang Ding

International Joint Conference on Artificial Intelligence

DOI

2025

LSNet: See Large, Focus Small

Ao Wang, Hui Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

Computer Vision and Pattern Recognition

DOI

2025

融合注意力机制和多尺度特征的无人机图像分割方法

王喜笑，陈辉

《山东理工大学学报(自然科学版)》

DOI

2025

基于深度学习的帕金森病磁共振图像辅助诊断

陶国庆，王靖涵，林雨莹，傅博涵，罗黔琴，陈辉

《光学仪器》

2025

基于改进ResNet的多标签胸部X光图像分类

方燕燕，陈辉

《山东理工大学学报(自然科学版)》

DOI

2024

YOLOv10: Real-Time End-to-End Object Detection

Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

Neural Information Processing Systems

DOI

2024

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

Yizhe Xiong, Hui Chen, Tianxiang Hao, Zijia Lin, Jun-Gong Han, Yuesong Zhang, Guoxin Wang, Yongjun Bao, Gui-Guang Ding

European Conference on Computer Vision

DOI

2024

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

Hui Yang, Hui Chen, Ao Wang, Kai Chen, Zijia Lin, Yongliang Tang, Pengcheng Gao, Yu Quan, Jun-Gong Han, Gui-Guang Ding

AAAI Conference on Artificial Intelligence

DOI

2024

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

Ao Wang, Hui Chen, Jiaxi Li, Jian-Chao Tan, Ke-Feng Zhang, Xun-Liang Cai, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

Neural Information Processing Systems

DOI

2024

A Simple Confidence-Supervised Model for High-Resolution Defect Recognition

Hui Yang, Hui Chen, Fan Zhang, X. Tian, Luning Zhu, Gui-Guang Ding

International Conference on Robotics, Control and Automation

DOI

2024

YOLO-UniOW: Efficient Universal Open-World Object Detection

Lihao Liu, Juexiao Feng, Hui Chen, Ao Wang, Lin Song, Jun-Gong Han, Gui-Guang Ding

arXiv.org

DOI

2024

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Ao Wang, Fengyuan Sun, Hui Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

arXiv.org

DOI

2024

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

Mengyao Lyu, Tianxiang Hao, Xinhao Xu, Hui Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

European Conference on Computer Vision

DOI

2024

Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection

Hui Yang, Hui Chen, Lihao Liu, Zijia Lin, Kai Chen, Lie-Jun Wang, Jun-Gong Han, Gui-Guang Ding

European Conference on Artificial Intelligence

DOI

2024

基于多尺度残差和注意力机制的图像去雾算法

陈辉，牛丽丽，付辉，张天佑，席磊

《兰州理工大学学报》

2024

一种四轴飞行器单目视觉测距算法

顾兆军，韩强，王家亮，陈辉，董楷

《小型微型计算机系统》

2024

视觉深度学习模型压缩加速综述

丁贵广，陈辉，王澳，杨帆，熊翊哲，梁伊雯

《智能系统学报》

2024

基于双目结构光的手机中框特征提取研究

邓锋，赵德安，姬伟，李长峰，陈辉，马腾

《软件导刊》

2024

基于残差卷积与多头自注意力的CXR图像分类

陈辉，张甜，陈润斌

《工程科学与技术》

2023

Rep ViT: Revisiting Mobile CNN From ViT Perspective

Ao Wang, Hui Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

Computer Vision and Pattern Recognition

DOI

2023

Box-Level Active Detection – Supplementary Material

Mengyao Lyu, Jun-Dong Zhou, Hui Chen, Yijie Huang, Dongdong Yu, Yaqian Li, Yan-Dong Guo, Yu-Cheng Guo, Liuyu Xiang, Gui-Guang Ding

2023

Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels

Zixuan Ding, Ao Wang, Hui Chen, Q. Zhang, Pengzhang Liu, Yong-Jun Bao, Weipeng P. Yan, Jungong Han

Computer Vision and Pattern Recognition

DOI

2023

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability

Tianxiang Hao, Mengyao Lyu, Hui Chen, Sicheng Zhao, Xiaohan Ding, Jun-Gong Han, Gui-Guang Ding

2023

Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation

Tian-Xiang Hao, Hui Chen, Yuchen Guo, Gui-Guang Ding

International Conference on Learning Representations

DOI

2023

RepViT-SAM: Towards Real-Time Segmenting Anything

Ao Wang, Hui Chen, Zijia Lin, Jun-Gong Han, Gui-Guang Ding

arXiv.org

DOI

2023

One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications

Mengyao Lyu, Yu-Hong Yang, Hai-Wen Hong, Hui Chen, Xuan Jin, Yuan He, Hui Xue, Jun-Gong Han, Gui-Guang Ding

Computer Vision and Pattern Recognition

DOI

2023

Box-Level Active Detection

Mengyao Lyu, Jun-Dong Zhou, Hui Chen, Yijie Huang, Dongdong Yu, Yaqian Li, Yandong Guo, Yuchen Guo, Liuyu Xiang, Gui-Guang Ding

Computer Vision and Pattern Recognition

DOI

2023

基于点云补全的三维目标检测

陈辉，王帅杰，蔡晗

《电子技术应用》

2023

基于深度学习的香梨表面腐烂图像识别研究

陈辉

《塔里木大学》

2023

基于深度学习的单幅图像去雨算法研究

陈辉

《南京邮电大学》

2023

基于计算机视觉的可见光图像彩色成像研究

刘倩，陈辉，曾健友

《激光杂志》

2023

融合多尺度特征和多重注意力的乳腺癌图像分类方法

韩玉静，陈辉

《宁夏师范大学学报》

2022

Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection

Fan Yang, Xinhao Xu, Hui Chen, Yuchen Guo, Jungong Han, K. Ni, Gui-Guang Ding

arXiv.org

DOI

2022

Contrastive Active Learning Under Class Distribution Mismatch

Pan Du, Hui Chen, Suyun Zhao, Shuwen Chai, Hong Chen, Cui-Ping Li

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2022

基于航拍图像的绝缘子目标检测与缺陷识别的研究

陈辉

《华北电力大学(北京)》

2022

融合PointNet和3D-LMNet的单幅图像三维重建及语义分割

陈辉，童勇，朱莉，梁维斌

《激光与光电子学进展》

2022

面向糖网小目标检测的反卷积神经网络方法

彭志浩，陈辉，张欣鹏，武继刚

《计算机应用与软件》

2021

基于图像处理的蛋鸡体重估测方法研究

郭蓓佳，籍颖，锡建中，周荣艳，陈辉，王德贺

《中国家禽》

2020

ACMNet

Hui Chen, Gui-Guang Ding, Zijia Lin, Sicheng Zhao, Xiao-Peng Gu, Wen-Yuan Xu, Jun-Gong Han

ACM Trans. Multim. Comput. Commun. Appl.

DOI

2020

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

Hui Chen, Gui-Guang Ding, Xu-Dong Liu, Zijia Lin, Ji Liu, Jungong Han

Computer Vision and Pattern Recognition

DOI

2020

基于标准路牌的车辆自定位

张善彬，袁金钊，陈辉，王玉荣，王杰，屠长河

《计算机科学》

2020

基于深度学习的单幅图像三维重建算法

朱莉，陈辉

《吉林化工学院学报》

DOI

2020

基于卷积神经网络的驾驶员异常姿态识别方法研究

陈辉

《大连理工大学》

2020

基于面部视频分析的生命体征检测

陈辉，郑秀娟，倪宗军，张昀，杨晓梅

《北京航空航天大学学报》

DOI

2020

基于动态网格k邻域搜索的激光点云精简算法

陈辉，黄晓铭，刘万泉

《控制与决策》

DOI

2018

Attend to Knowledge: Memory-Enhanced Attention Network for Image Captioning

Hui Chen, Gui-Guang Ding, Zijia Lin, Yuchen Guo, J. Han

International Conference on Advances in Brain Inspired Cognitive Systems

DOI

2018

Temporal-Difference Learning With Sampling Baseline for Image Captioning

Hui Chen, Gui-Guang Ding, Sicheng Zhao, J. Han

AAAI Conference on Artificial Intelligence

DOI

2018

Show, Observe and Tell: Attribute-driven Attention Model for Image Captioning

Hui Chen, Gui-Guang Ding, Zijia Lin, Sicheng Zhao, J. Han

International Joint Conference on Artificial Intelligence

DOI

2018

Neural Image Caption Generation with Weighted Training and Reference

Gui-Guang Ding, Minghai Chen, Sicheng Zhao, Hui Chen, J. Han, Qiang Liu

Cognitive Computation

DOI

2017

Reference Based LSTM for Image Captioning

Minghai Chen, Gui-Guang Ding, Sicheng Zhao, Hui Chen, Qiang Liu, J. Han

AAAI Conference on Artificial Intelligence

DOI

2016

基于激光扫描和SFM的非同步点云三维重构方法

陈辉，马世伟，Andreas Nuechter

《仪器仪表学报》

2016

智能视频分析技术在食用袋盐计数系统的应用研究

陈辉，李兵

《中国盐业》

2013

基于反射与透射图像的糯玉米叶片机器视觉识别效果分析

邓立苗，陈辉，马文杰

《粮油食品科技》

2010

用于内容认证的半脆弱可逆视频水印算法

曾骁，陈真勇，范围，陈辉，熊璋

《中国图象图形学报》

2009

由未标定手持相机拍摄的图片构造全景图

陈辉，龙爱群，彭玉华

《计算机学报》

2009

浅议车牌识别中字符的特征提取方法

陈辉

《科技传播》

2007

一种改进的全景图自动拼接算法

赵辉，陈辉，于泓

《中国图象图形学报》

2007

一种动态场景下基于时空信息的视频对象提取算法

田宏阳，陈辉，马文静

《中国图象图形学报》

2004

人脸表情的混沌仿生识别

陈辉，张家树

《仪器仪表学报》

DOI

精选作品

期刊论文

RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance

DINO-PCB: Two-stage vision foundation model pretraining and distillation for real-time circuit-board defect detection

融合注意力机制的CNN-Mamba的医学图像分割方法

融合注意力机制和多层次特征的结肠息肉分割方法

基于混合局部通道注意力机制的水下光学图像目标检测算法

面向遥感图像的改进RT-DETR目标检测算法

基于改进YOLOv7的遥感图像目标检测方法

Enhanced underwater object detection via multi-scale attention and adaptive feature fusion

Enhancing underwater debris detection: a dimension-aware diffusion and progressive feature enhancement approach

Frequency-decoupled multi-scale hybrid transformer for underwater object detection

DAR-Prompt: Dynamic Regulation in Prompt Tuning for Multi-Label Zero-Shot Learning

YOLOE: Real-Time Seeing Anythi

Exploiting Position Information in Convolutional Kernels for Structural Re-parameterization

LSNet: See Large, Focus Small

融合注意力机制和多尺度特征的无人机图像分割方法

基于深度学习的帕金森病磁共振图像辅助诊断

基于改进ResNet的多标签胸部X光图像分类

YOLOv10: Real-Time End-to-End Object Detection

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

A Simple Confidence-Supervised Model for High-Resolution Defect Recognition

YOLO-UniOW: Efficient Universal Open-World Object Detection

[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs

Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence

Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection

基于多尺度残差和注意力机制的图像去雾算法

一种四轴飞行器单目视觉测距算法

视觉深度学习模型压缩加速综述

基于双目结构光的手机中框特征提取研究

基于残差卷积与多头自注意力的CXR图像分类

Rep ViT: Revisiting Mobile CNN From ViT Perspective

Box-Level Active Detection – Supplementary Material

Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability

Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation

RepViT-SAM: Towards Real-Time Segmenting Anything

One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications

Box-Level Active Detection

基于点云补全的三维目标检测

基于深度学习的香梨表面腐烂图像识别研究

基于深度学习的单幅图像去雨算法研究

基于计算机视觉的可见光图像彩色成像研究

融合多尺度特征和多重注意力的乳腺癌图像分类方法

Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection

Contrastive Active Learning Under Class Distribution Mismatch

基于航拍图像的绝缘子目标检测与缺陷识别的研究

融合PointNet和3D-LMNet的单幅图像三维重建及语义分割

面向糖网小目标检测的反卷积神经网络方法

基于图像处理的蛋鸡体重估测方法研究

ACMNet

IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval

基于标准路牌的车辆自定位

基于深度学习的单幅图像三维重建算法

基于卷积神经网络的驾驶员异常姿态识别方法研究

基于面部视频分析的生命体征检测

基于动态网格k邻域搜索的激光点云精简算法

Attend to Knowledge: Memory-Enhanced Attention Network for Image Captioning

Temporal-Difference Learning With Sampling Baseline for Image Captioning

Show, Observe and Tell: Attribute-driven Attention Model for Image Captioning

Neural Image Caption Generation with Weighted Training and Reference

Reference Based LSTM for Image Captioning

基于激光扫描和SFM的非同步点云三维重构方法

智能视频分析技术在食用袋盐计数系统的应用研究

基于反射与透射图像的糯玉米叶片机器视觉识别效果分析

用于内容认证的半脆弱可逆视频水印算法

由未标定手持相机拍摄的图片构造全景图

浅议车牌识别中字符的特征提取方法

一种改进的全景图自动拼接算法

一种动态场景下基于时空信息的视频对象提取算法

人脸表情的混沌仿生识别

研究方向