智敏｜内蒙古师范大学｜学者主页

2026

视觉Mamba：结构、应用与前景

张鑫，智敏，萨茹拉，阿日木扎

《计算机科学与探索》

2026

Semantic Topological Multi-Scale Part Network for Fine-Grained Visual Classification

Xuerong Liu, Min Zhi, Yanjun Yin, Rula Sa

Journal of Imaging

DOI

2026

Rethinking Hyperspectral Representation: A Transformer Driven by Intrinsic Spectral Harmonics

Chenyu Liu, Min Zhi, Yanjun Yin, Qiaozhi Xu, Xuerong Liu, Yuhao Wu

Lecture notes in computer science

DOI

2026

GPR-Net: Geometric Part Relationship Modeling for Fine-Grained Visual Classification

Xuerong Liu, Min Zhi, Xuhao Wu, Chenyu Liu, Yanjun Yin, Ping Ping, Rula Sa

Lecture notes in computer science

DOI

2026

SDG: Semantic Saliency-Guided Prototypical Graph Network for Few-Shot Segmentation

Zhichen Hou, Yanjun Yin, Min Zhi, Qiaozhi Xu

Lecture notes in computer science

DOI

2026

DFFNet: Transformer-Based Pedestrian Re-Identification Network with Dynamic Frequency Focusing and Heterogeneous Spatial Displacement

Yuhao Wu, Min Zhi, Xuerong Liu, Chenyu Liu, Qiaozhi Xu, Sarula

Lecture notes in computer science

DOI

2026

Few-shot Semantic Segmentation with Multi-scale Foreground Guidance and Dynamic Prototype Alignment

Zhichen Hou, Yanjun Yin, Qiaozhi Xu, Min Zhi

Lecture notes in computer science

DOI

2026

Adaptive Sparse Spectral-Spatial Fusion Mamba for Hyperspectral Image Classification

Chenyu Liu, Min Zhi, Yanjun Yin, PingPing, Qiaozhi Xu, Xuerong Liu, Yuhao Wu

Lecture notes in computer science

DOI

2026

SHDMambaNet: Safety Helmet Detection Mamba Network Based on Multi-scale Feature Aggregation

Jiabao Qi, Min Zhi, Qiaozhi Xu

Communications in computer and information science

DOI

2026

Fine-Grained Recognition of Sheep Faces Based on Multi-path Feature Fusion

Xuerong Liu, Min Zhi, J Q, Shixiong Wen, Yanjun Yin, Qiaozhi Xu, Ping Ping

Lecture notes in computer science

DOI

2025

深度学习下的单阶段通用目标检测算法研究综述

王宁，智敏

《计算机科学与探索》

2025

图像处理中CNN与视觉Transformer混合模型研究综述

郭佳霖，智敏，殷雁君，葛湘巍

《计算机科学与探索》

2025

一种轻量级脑胶质瘤分割模型

呼伟，杨鸿杰，徐巧枝，智敏，萨和雅，于磊

《郑州大学学报(理学版)》

DOI

2025

一种多级别多尺度上下文特征融合的玻璃面分割算法

任晓宇，智敏

《计算机应用与软件》

2025

A Review of Frequency-Domain Transformers in Image Processing Applications

ChunWang Li, Jialin Guo, Min Zhi

International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)

DOI

2025

SRDNet: Style Representation Disentanglement Network for Few- Shot Semantic Segmentation

Yuxin Xia, Yanjun Yin, Qiaozhi Xu, Min Zhi

Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics

DOI

2025

Dual-Decoupling and Multi-Level Feature Integration for Cross-Age Face Recognition

Wentao Duan, Min Zhi, Ping Ping, Yuening Zhang, Xuanhao Qi, Wei Dong Hu, Zhe Lian

Chinese Journal of Electronics

DOI

2025

FCFormer: Fourier Convolution Vision Transformer for Image Classification

Jialin Guo, Min Zhi, Yanjun Yin, Qiaozhi Xu

Lecture notes in computer science

DOI

2025

WSFFormer: LightWeight Wavelet Spatial-Frequency Vision Transformer for Visual Representation Learning

Jialin Guo, Min Zhi, Yanjun Yin, Qiaozhi Xu, Yuxin Xia

Lecture notes in computer science

DOI

2025

Cross-Modal Prior Generation and Structured Information Fusion for Few-Shot Semantic Segmentation

Shiyuan Liu, Yanjun Yin, Min Zhi, Qiaozhi Xu, Ruizhe Zhang, Yuxin Xia

International Conference on Intelligent Computing

DOI

2025

Feature-Guided Prototype-Enhanced Few-Shot Semantic Segmentation Model

Shiyuan Liu, Yanjun Yin, Min Zhi, Qiaozhi Xu, Ruizhe Zhang, Yuxin Xia

International Conference on Intelligent Computing

DOI

2024

基于时空注意图卷积的人体动作识别

赵登阁，智敏

《计算机应用与软件》

2024

基于MAPFormer的人体动作识别研究

陆静芳，智敏

《内蒙古师范大学学报(自然科学版)》

2024

融合CNN与Transformer的跨年龄人脸识别

刘二毛，智敏

《内蒙古师范大学学报(自然科学版)》

2024

自然场景文本检测中可微分二值化技术综述

连哲，殷雁君，智敏，徐巧枝

《计算机科学与探索》

2024

图像处理中注意力机制综述

祁宣豪，智敏

《计算机科学与探索》

2024

面向图像分类的Vision Transformer研究综述

智敏，陆静芳

《郑州大学学报(工学版)》

2024

多尺度特征提取和双向特征融合的场景文本检测

连哲，殷雁君，智敏，徐巧枝

《哈尔滨理工大学学报》

2024

融合多层级特征的跨年龄人脸识别方法

段文涛，智敏

《计算机工程与设计》

2024

LDCFormer: A Lightweight Approach to Spectral Channel Image Recognition

Xuanhao Qi, Min Zhi, Yanjun Yin, Xiangwei Ge, Qiaozhi Xu, Wentao Duan

DOI

2024

A Cross-Age Face Recognition Method Utilizing Non-linear Decoupling of Multi-level Features

Wentao Duan, Min Zhi, Yanjun Yin, Xiangwei Ge, Xuanhao Qi, Wei Dong Hu

DOI

2024

SFAM: Lightweight Spectrum Unreferenced Attention Network

Xuanhao Qi, Min Zhi, Yanjun Yin, Ping Ping, Yuening Zhang

International Conference on Multimedia Retrieval

DOI

2024

A Survey: Feature Fusion Method for Object Detection Field

Zhe Lian, Yanjun Yin, Jingfang Lu, Qiaozhi Xu, Min Zhi, Wei Hu, Wentao Duan

Lecture notes in computer science

DOI

2024

A Review of Cross-Age Facial Recognition Based on Discriminative Models

Wentao Duan, Min Zhi, Ping Ping, Xiangwei Ge, Yuening Zhang, Xuanhao Qi, Wei Hu, Zhe Lian

Lecture notes in computer science

DOI

2024

Refinement Correction Network for Scene Text Detection

Zhe Lian, Yanjun Yin, Wei Dong Hu, Qiaozhi Xu, Min Zhi, Jingfang Lu, Xuanhao Qi

Lecture notes in computer science

DOI

2024

PAAM (Parameter-free Attentional Aggregation Model)

Xuan-Hao Qi, Min Zhi, Zeng Mi, Wei Hu, Yanjun Yin, Yue-Ning Zhang, Wen-Tao Duan, Zhe Lian

Lecture notes in computer science

DOI

2024

A Review of Vision Transformer for Image Classification

ZHI Min, LU Jingfang

DOAJ (DOAJ: Directory of Open Access Journals)

DOI

2024

Unsupervised Domain Adaptation Method for Medical Image Segmentation Using Fourier Feature Decoupling and Multi-scale Feature Fusion

Wei Hu, Qiaozhi Xu, Z. Lian, Yanjun Yin, Min Zhi, Na Yang, Wentao Duan, Lei Yu

International Conference on Intelligent Computing

DOI

2024

Unsupervised Domain Adaptation in Medical Image Segmentation via Fourier Feature Decoupling and Multi-teacher Distillation

Wei Hu, Qiaozhi Xu, Xuan-Hao Qi, Yanjun Yin, Min Zhi, Z. Lian, Na Yang, Wentao Duan, Lei Yu

International Conference on Intelligent Computing

DOI

2023

用于人体动作识别的多尺度时空图卷积算法

赵登阁，智敏

《计算机科学与探索》

2023

基于上下文注意的强化学习目标检测

曹立春，智敏

《计算机应用与软件》

2023

融合边缘注意力的手写蒙古文字元数据增强方法

石佳钰，殷雁君，张文轩，智敏

《内蒙古师范大学学报(自然科学版)》

2023

A Review of Attention Mechanisms in Computer Vision

Xuanhao Qi, Min Zhi

International Conference on Image, Vision and Computing (ICIVC)

DOI

2023

Review of Cross-Age Face Recognition in Discriminative Models

Liu Ermao, Min Zhi

International Conference on Image, Vision and Computing (ICIVC)

DOI

2023

PCBSNet: A Pure Convolutional Bilateral Segmentation Network for Real-Time Natural Scene Text Detection

Zhe Lian, Yanjun Yin, Min Zhi, Qiaozhi Xu

Electronics

DOI

2022

基于2D CNN和Transformer的人体动作识别

朱相华，智敏，殷雁君

《电子测量技术》

2022

基于改进深度学习方法的人体动作识别综述

朱相华，智敏

《计算机应用研究》

2022

CNN和Transformer在细粒度图像识别中的应用综述

马瑶，智敏，殷雁君，萍萍

《计算机工程与应用》

2022

Summary of fine-grained image recognition based on attention mechanism

Yao Ma, Min Zhi

International Conference on Graphics and Image Processing (ICGIP)

DOI

2022

A review of action recognition methods based on skeleton data

Dengge Zhao, Min Zhi

International Conference on Graphics and Image Processing (ICGIP)

DOI

2022

An overview of traffic sign detection and recognition algorithms

Xiaoyu Ren, Min Zhi

International Conference on Graphics and Image Processing (ICGIP)

DOI

2022

Review of human action recognition based on improved deep learning methods

Zhu Xianghua, Min Zhi

International Conference on Graphics and Image Processing (ICGIP)

DOI

2021

Norm-DP模型行人检测优化算法

柴恩惠，马占飞，智敏

《计算机科学与探索》

2021

基于可变形卷积神经网络的人体动作识别

王雪娇，智敏

《计算机工程与科学》

2021

基于推理网络的人体动作识别

葛鹏花，智敏

《计算机工程与设计》

DOI

2021

基于改进的VGG-Net的手写蒙古文字元识别

石佳钰，殷雁君，刁明皓，智敏

《内蒙古师范大学学报(自然科学版)》

2021

ERF-YOLO: A YOLO algorithm compatible with fewer parameters and higher accuracy

En-Hui Chai, Lin Ta, Zhan-Fei Ma, Min Zhi

Image and Vision Computing

DOI

2020

基于双流独立循环神经网络的人体动作识别

葛鹏花，智敏，于华，郝岩

《现代电子技术》

DOI

2020

Driving State Recognition for Ego-central Driving Videos

Guimei Qi, Li Du, Min Zhi, Qing Yong

International Conference on Computer and Communication Systems (ICCCS)

DOI

2020

Summary of object detection based on convolutional neural network

Xuejiao Wang, Min Zhi

International Conference on Graphics and Image Processing (ICGIP)

DOI

2019

基于改进CNN框架的人体动作识别

于华，智敏

《计算机工程与设计》

DOI

2019

基于卷积神经网络的人体动作识别

于华，智敏

《计算机工程与设计》

DOI

2019

Human action recognition based on two-stream Ind recurrent neural network

Penghua Ge, Min Zhi

International Conference on Graphics and Image Processing (ICGIP)

DOI

2017

一种基于MHI和支持向量机的人体动作识别方法

周佳琪，智敏

《软件导刊》

2017

Rapid pedestrian detection algorithm based on deformable part model

Enhui Chai, Min Zhi

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

DOI

2015

Moving Object Detection in Tennis Video

Yanjiang Liu, Min Zhi

International Conference on Intelligent Networks and Intelligent Systems

DOI

2013

Adaptive threshold based slow motion replay detection method for tennis video

Min Zhi

Computer Engineering and Science

2012

Slow motion replay detection of tennis video based on color auto-correlogram

Xiaoli Zhang, Min Zhi

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

DOI

2009

Scenery video type classification based on SVM

Min Zhi

Asia Pacific Conference on Postgraduate Research in Microelectronics & Electronics (PrimeAsia)

DOI

2009

MPEG-7 Feature Based Shot Change Detection for Scenery Video

Min Zhi

DOI

2009

A Scene-based Video Summary Generation Algorithm

Min Zhi

Journal of Inner Mongolia University

2007

基于基色调的镜头边界检测方法

智敏，蔡安妮

《自动化学报》

2007

Key frame extraction from scenery video

Min Zhi

International Conference on Wavelet Analysis and Pattern Recognition

DOI

2006

一种家庭视频摘要生成的新方法

智敏，蔡安妮

《计算机工程》

2005

Shot change detection with adaptive thresholds

Min Zhi, Anni Cai

DOI

精选作品

期刊论文

视觉Mamba：结构、应用与前景

Semantic Topological Multi-Scale Part Network for Fine-Grained Visual Classification

Rethinking Hyperspectral Representation: A Transformer Driven by Intrinsic Spectral Harmonics

GPR-Net: Geometric Part Relationship Modeling for Fine-Grained Visual Classification

SDG: Semantic Saliency-Guided Prototypical Graph Network for Few-Shot Segmentation

DFFNet: Transformer-Based Pedestrian Re-Identification Network with Dynamic Frequency Focusing and Heterogeneous Spatial Displacement

Few-shot Semantic Segmentation with Multi-scale Foreground Guidance and Dynamic Prototype Alignment

Adaptive Sparse Spectral-Spatial Fusion Mamba for Hyperspectral Image Classification

SHDMambaNet: Safety Helmet Detection Mamba Network Based on Multi-scale Feature Aggregation

Fine-Grained Recognition of Sheep Faces Based on Multi-path Feature Fusion

深度学习下的单阶段通用目标检测算法研究综述

图像处理中CNN与视觉Transformer混合模型研究综述

一种轻量级脑胶质瘤分割模型

一种多级别多尺度上下文特征融合的玻璃面分割算法

A Review of Frequency-Domain Transformers in Image Processing Applications

SRDNet: Style Representation Disentanglement Network for Few- Shot Semantic Segmentation

Dual-Decoupling and Multi-Level Feature Integration for Cross-Age Face Recognition

FCFormer: Fourier Convolution Vision Transformer for Image Classification

WSFFormer: LightWeight Wavelet Spatial-Frequency Vision Transformer for Visual Representation Learning

Cross-Modal Prior Generation and Structured Information Fusion for Few-Shot Semantic Segmentation

Feature-Guided Prototype-Enhanced Few-Shot Semantic Segmentation Model

基于时空注意图卷积的人体动作识别

基于MAPFormer的人体动作识别研究

融合CNN与Transformer的跨年龄人脸识别

自然场景文本检测中可微分二值化技术综述

图像处理中注意力机制综述

面向图像分类的Vision Transformer研究综述

多尺度特征提取和双向特征融合的场景文本检测

融合多层级特征的跨年龄人脸识别方法

LDCFormer: A Lightweight Approach to Spectral Channel Image Recognition

A Cross-Age Face Recognition Method Utilizing Non-linear Decoupling of Multi-level Features

SFAM: Lightweight Spectrum Unreferenced Attention Network

A Survey: Feature Fusion Method for Object Detection Field

A Review of Cross-Age Facial Recognition Based on Discriminative Models

Refinement Correction Network for Scene Text Detection

PAAM (Parameter-free Attentional Aggregation Model)

A Review of Vision Transformer for Image Classification

Unsupervised Domain Adaptation Method for Medical Image Segmentation Using Fourier Feature Decoupling and Multi-scale Feature Fusion

Unsupervised Domain Adaptation in Medical Image Segmentation via Fourier Feature Decoupling and Multi-teacher Distillation

用于人体动作识别的多尺度时空图卷积算法

基于上下文注意的强化学习目标检测

融合边缘注意力的手写蒙古文字元数据增强方法

A Review of Attention Mechanisms in Computer Vision

Review of Cross-Age Face Recognition in Discriminative Models

PCBSNet: A Pure Convolutional Bilateral Segmentation Network for Real-Time Natural Scene Text Detection

基于2D CNN和Transformer的人体动作识别

基于改进深度学习方法的人体动作识别综述

CNN和Transformer在细粒度图像识别中的应用综述

Summary of fine-grained image recognition based on attention mechanism

A review of action recognition methods based on skeleton data

An overview of traffic sign detection and recognition algorithms

Review of human action recognition based on improved deep learning methods

Norm-DP模型行人检测优化算法

基于可变形卷积神经网络的人体动作识别

基于推理网络的人体动作识别

基于改进的VGG-Net的手写蒙古文字元识别

ERF-YOLO: A YOLO algorithm compatible with fewer parameters and higher accuracy

基于双流独立循环神经网络的人体动作识别

Driving State Recognition for Ego-central Driving Videos

Summary of object detection based on convolutional neural network

基于改进CNN框架的人体动作识别

基于卷积神经网络的人体动作识别

Human action recognition based on two-stream Ind recurrent neural network

一种基于MHI和支持向量机的人体动作识别方法

Rapid pedestrian detection algorithm based on deformable part model

Moving Object Detection in Tennis Video

Adaptive threshold based slow motion replay detection method for tennis video

Slow motion replay detection of tennis video based on color auto-correlogram

Scenery video type classification based on SVM

MPEG-7 Feature Based Shot Change Detection for Scenery Video

A Scene-based Video Summary Generation Algorithm

基于基色调的镜头边界检测方法

Key frame extraction from scenery video

一种家庭视频摘要生成的新方法

Shot change detection with adaptive thresholds

研究方向