About Me Liu Wei, received the Ph.D. degree of Information and Communication Engineering in National University of Defense Technology (NUDT). Before that, he worked as a joint educated Ph.D. student in Institute of Automation, Chinese Academy of Sciences (CASIA), under the supervision of Dr. Liao Shengcai. E-mail: liuwei16@nudt.edu.cn Research Interest: Machine Learning and Computer Vision, with a focus on pedestrian detection, face detection, video object detection, domain adaptation and GAN

News

• 09 / 2019: One paper is accepted by TIP

• 03 / 2019: One paper is accepted by TCSVT

• 02 / 2019: One paper is accepted by CVPR 2019

• 02 / 2019: One paper is accepted by Neurocomping

• 07 / 2018: One paper is accepted by ECCV 2018

• 03 / 2018: Two papers are accepted by ICME 2018

Publications

High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection

• Wei Liu, Shengcai Liao, Weiqiang Ren, Weidong Hu and Yinan Yu
• IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
• paper, code

Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting

• Wei Liu, Shengcai Liao, Weidong Hu, Xuezhi Liang and Xiao Chen
• The European Conference on Computer Vision (ECCV), 2018
• paper, code, poster

Improving Tiny Vehicle Detection in Complex Scenes

• Wei Liu, Shengcai Liao, Weidong Hu, Xuezhi Liang and Yan Zhang
• IEEE International Conference on Multimedia and Expo (ICME), 2018
• paper, code

Perceiving Motion from Dynamic Memory for Vehicle Detection in Surveillance Videos

• Wei Liu, Shengcai Liao, Weidong Hu
• IEEE Transaction on Circuits and System for Video Technology (TCSVT), 2019
• paper

Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding

• Wei Liu, Shengcai Liao, Weidong Hu
• IEEE Transaction on Image Processing (TIP), 2019
• paper

Towards Accurate Tiny Vehicle Detection in Complex Scenes

• Wei Liu, Shengcai Liao, Weidong Hu
• Neurocomputing, 2019
• paper

Deep Background Subtraction with Guided Learning

• Xuezhi Liang, Shengcai Liao, Wei Liu
• IEEE International Conference on Multimedia and Expo (ICME), 2018

Academic Activities

Presentation

• CVPR 2019 Poster
• ECCV 2018 Poster
• ICME 2018 Oral presentation

Reviewer

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
• AAAI Conference on Artificial Intelligence (AAAI), 2019
• International Conference on Pattern Recognition (ICPR), 2018
• Chinese Conference on Biometric Recognition (CCBR), 2017
• Neurocomputing

Education

PhD student, College of Electronic Science, National University of Defense Technology (NUDT) Mar. 2016 - Sep. 2019, Supervised by Prof. Hu Weidong

Joint educated PhD student, Institute of Automation, Chinese Academy of Sciences (CASIA) June 2017 - Mar. 2019, Supervised by Dr. Liao Shengcai

Awards

• The Winner, CVPR 2017 Detection in Crowded Scenes Challenge (MOT17Det), Honolulu, Hawaii, USA, July 21-26, 2017.

• The fifth place, ECCV2018 WIDER Challenge on the pedestrian detection track, Munich, Germany, Sep. 8-14 2018.