个人简介
刘威，男，1991年生，副教授。2020年于国防科技大学电子科学学院获得工学博士学位。2023年9月加入常熟理工学院计算机科学与工程学院，从事教学与科研工作。
主要研究兴趣包括模式识别、计算机视觉和多模态深度学习及应用等。目前已在《Pattern Recognition》《IEEE Transactions on Image Processing》《IEEE Transaction on Circuits and System for Video Technology》等国际知名期刊和《CVPR》《ECCV》等计算机视觉领域顶级会议以第一作者身份发表论文7篇，Google学术累计引用764次，H-index为7，单篇最高引用409次，申请国家发明专利5项，已获授权1项.

研究方向
计算机视觉，多模态深度学习及应用
主要承担的教学课程
数字图像处理

代表性学术成果
期刊论文：
[1] Wei Liu; Irtiza Hasan; Shengcai Liao ; Center and Scale Prediction: A Box-free Approach for Pedestrian and Face Detection, Pattern Recognition, 2023, 135: 109071
[2] Wei Liu; Shengcai Liao; Weidong Hu ; Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding, IEEE Transactions on Image Processing, 2019.冬季, 29(99): 1413-1425
[3] Wei Liu; Shengcai Liao; Weidong Hu ; Perceiving Motion from Dynamic Memory for Vehicle Detection in Surveillance Videos, IEEE Transactions on Circuits & Systems for Video Technology, 2019.春季, 29(12): 3558-3567
[4] Wei Liu, Shengcai Liao, Weidong Hu. "Towards Accurate Tiny Vehicle Detection in Complex Scenes". Neurocomputing, 2019
会议论文：
[5] Wei Liu; Shengcai Liao; Weiqiang Ren; Weidong Hu; Yinan Yu ; High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019
[6] Wei Liu; Shengcai Liao; Weidong Hu; Xuezhi Liang; Xiao Chen ; Learning Efficient Single- stage Pedestrian Detection by Asymptotic Localization Fitting, European Conference on Computer Vision (ECCV), Munich, Germany, 2018
[7] Wei Liu, Shengcai Liao, Weidong Hu, Xuezhi Liang, Yan Zhang. Improving Tiny Vehicle Detection In Complex Scenes. IEEE International Conference on Multimedia and Expo (ICME), 2018: 1-6

发明专利：
[1] 廖胜才; 刘威 ; 基于动态记忆和运动感知的目标检测方法及系统, 2019-01-11, 中国, CN201811028891.6

联系方式
Email：liuwei@cslg.edu.cn