刘军｜武汉工程大学｜学者主页

2025

Radar M3-Net: Multi-scale, multi-layer, multi-frame network with a large receptive field for 3D object detection

Yunting Yang, Jun Liu, Hongsi Liu, Guangfeng Jiang

Expert Systems With Applications，Vol. 286

DOI

2025

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

Jingmin Zhu, Anqi Zhu, Hossein Rahmani, Jun Liu, Mohammed Bennamoun, Qiu-Hong Ke

Neural Information Processing Systems

DOI

2025

DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition

Jingmin Zhu, Anqi Zhu, James Bailey, Jun Liu, Hossein Rahmani, Mohammed Bennamoun, F. Boussaid, Qiu-Hong Ke

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2025

TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition

Yanan Liu, Jun Liu, Hao Zhang, Dan Xu, Hossein Rahmani, Mohammed Bennamoun, Qiu-Hong Ke

arXiv.org

DOI

2025

Endoscopic Image Enhancement Method Based on Improved Attention Mechanism

Yuxin Wang, Shaofei Wu, Jun Liu, Leyan Wang, Nan Zhou, Yan Qin

DOI

2024

用于奶油色素定量分析的注意力残差网络设计与验证

张芸，宋刚，刘军，谭正林，黄晓彤

《武汉工程大学学报》

2023

Self-Supervised 3D Action Representation Learning With Skeleton Cloud Colorization

Siyuan Yang, Jun Liu, Shi-Jian Lu, Er Meng Hwa, Yongjian Hu, A. Kot

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2023

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

Siyuan Yang, Jun Liu, Shi-Jian Lu, Er Meng Hwa, A. Kot

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2023

Dear-Net: Learning Diversities for Skeleton-Based Early Action Recognition

Rui Wang, Jun Liu, Qiu-Hong Ke, Duo Peng, Yin-Jie Lei

IEEE transactions on multimedia

DOI

2022

Calculation of Salt Heap Volume Based on Point Cloud Surface Reconstruction

Chuang LIU, Jun Liu, Meijuan Zhang, Ruirui Liu, Guangfeng Dong, Zhen Wang, Zhongjian Liu

International Conference on Robotics and Computer Vision (ICRCV)

DOI

2021

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Siyuan Yang, Jun Liu, Shi-Jian Lu, Meng Hwa Er, A. Kot

IEEE International Conference on Computer Vision

DOI

2021

Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data

Tianjiao Li, Qiuhong Ke, Hossein Rahmani, Rui-En Ho, Henghui Ding, Jun Liu

IEEE International Conference on Computer Vision

DOI

2021

A spatial attentive and temporal dilated (SATD) GCN for skeleton-based action recognition

Jiaxu Zhang, Gaoxiang Ye, Zhigang Tu, Yong Qin, Qianqing Qin, Jinlu Zhang, Jun Liu

CAAI Transactions on Intelligence Technology

DOI

2021

3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve

Lei Wang, Jun Liu, Piotr Koniusz

arXiv.org

2021

The Saline Terrain Prediction Model Based on Random Forest

Ribian Huang, Jun Liu, Jianxing Zhang, Guangfeng Dong, Zhen Wang, Zhongjian Liu

International Conference on Robotics, Control and Automation Engineering (RCAE)

DOI

2019

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

Jun Liu, Amir Shahroudy, Mauricio Perez, G. Wang, Ling-Yu Duan, A. Kot

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2019

Interaction Recognition Through Body Parts Relation Reasoning

Mauricio Perez, Jun Liu, A. Kot

Asian Conference on Pattern Recognition

DOI

2018

Global Regularizer and Temporal-Aware Cross-Entropy for Skeleton-Based Early Action Recognition

Qiuhong Ke, Jun Liu, Bennamoun, H. Rahmani, S. An, Ferdous Sohel, Farid Boussaïd

Asian Conference on Computer Vision

DOI

2018

Robust 3-D Human Detection in Complex Environments With a Depth Camera

Luchao Tian, Mingchen Li, Yu Hao, Jun Liu, Guyue Zhang, Yan-Qiu Chen

IEEE transactions on multimedia

DOI

2018

SSNet: Scale Selection Network for Online 3D Action Prediction

Jun Liu, Amir Shahroudy, G. Wang, Ling-Yu Duan, A. Kot

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

DOI

2018

Computer Vision for Human-Machine Interaction

Qiu-Hong Ke, Jun Liu, Bennamoun, S. An, Ferdous Sohel, F. Boussaid

DOI

2017

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

Jun Liu, G. Wang, Ping Hu, Ling-Yu Duan, A. Kot

Computer Vision and Pattern Recognition

DOI

2017

Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks

Jun Liu, G. Wang, Ling-Yu Duan, Kamila Abdiyeva, A. Kot

IEEE Transactions on Image Processing

DOI

2017

Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos

Guyue Zhang, Jun Liu, Hengduo Li, Yan-Qiu Chen, L. Davis

IEEE Signal Processing Letters

DOI

2017

Multi-glimpse LSTM with color-depth feature fusion for human detection

Hengduo Li, Jun Liu, Guyue Zhang, Yuan Gao, Yi-Rui Wu

International Conference on Information Photonics

DOI

2017

Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates

Jun Liu, Amir Shahroudy, Dong Xu, A. Kot, G. Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2016

Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

Jun Liu, Amir Shahroudy, Dong Xu, Gang Wang

European Conference on Computer Vision

DOI

2016

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Amir Shahroudy, Jun Liu, T. Ng, G. Wang

Computer Vision and Pattern Recognition

DOI

2016

Reliably detecting humans in crowded and dynamic environments using RGB-D camera

Luchao Tian, Guyue Zhang, Mingchen Li, Jun Liu, Yan-Qiu Chen

IEEE International Conference on Multimedia and Expo

DOI

2016

Reliably detecting humans with RGB-D camera with physical blob detector followed by learning-based filtering

Guyue Zhang, Jun Liu, Luchao Tian, Yan-Qiu Chen

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2016

Robust Real-Time Human Perception with Depth Camera

Guyue Zhang, Luchao Tian, Ye Liu, Jun Liu, X. Liu, Yang Liu, Yan-Qiu Chen

European Conference on Artificial Intelligence

DOI

2015

An ultra-fast human detection method for color-depth camera

Jun Liu, Guyue Zhang, Ye Liu, Luchao Tian, Yan-Qiu Chen

Journal of Visual Communication and Image Representation

DOI

2015

Detecting and tracking people in real time with RGB-D camera

Jun Liu, Ye Liu, Guyue Zhang, Peiru Zhu, Yan-Qiu Chen

Pattern Recognition Letters

DOI

2013

Real-time human detection and tracking in complex environments using single RGBD camera

Jun Liu, Ye Liu, Ying Cui, Yan-Qiu Chen

2013 IEEE International Conference on Image Processing

DOI

2013

双目视觉立体标定方法的改进

刘军，李娜，刘鹏

《武汉工程大学学报》

刘军

精选作品

期刊论文

Radar M3-Net: Multi-scale, multi-layer, multi-frame network with a large receptive field for 3D object detection

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition

TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition

Endoscopic Image Enhancement Method Based on Improved Attention Mechanism

用于奶油色素定量分析的注意力残差网络设计与验证

Self-Supervised 3D Action Representation Learning With Skeleton Cloud Colorization

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

Dear-Net: Learning Diversities for Skeleton-Based Early Action Recognition

Calculation of Salt Heap Volume Based on Point Cloud Surface Reconstruction

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data

A spatial attentive and temporal dilated (SATD) GCN for skeleton-based action recognition

3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve

The Saline Terrain Prediction Model Based on Random Forest

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

Interaction Recognition Through Body Parts Relation Reasoning

Global Regularizer and Temporal-Aware Cross-Entropy for Skeleton-Based Early Action Recognition

Robust 3-D Human Detection in Complex Environments With a Depth Camera

SSNet: Scale Selection Network for Online 3D Action Prediction

Computer Vision for Human-Machine Interaction

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks

Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos

Multi-glimpse LSTM with color-depth feature fusion for human detection

Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates

Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

Reliably detecting humans in crowded and dynamic environments using RGB-D camera

Reliably detecting humans with RGB-D camera with physical blob detector followed by learning-based filtering

Robust Real-Time Human Perception with Depth Camera

An ultra-fast human detection method for color-depth camera

Detecting and tracking people in real time with RGB-D camera

Real-time human detection and tracking in complex environments using single RGBD camera

双目视觉立体标定方法的改进

研究方向