Mingxiang Liao  

Ph.D. candidate

Room 260, Academy 2 Building
School of Electronic, Electrical and Communication Engineering
University of Chinese Academy of Sciences
Beijing, China, 101408.

Email: liaomingxiang20@mails.ucas.ac.cn;
Github: https://github.com/MingxiangL;
Google Scholar: https://scholar.google.com

Biography

I am a Ph.D. candidate in LAMP (Learning And Machine Perception) in the School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences , advised by Prof. Qixiang Ye. I earned a B.E. from the Harbin Institute of Technology, Shenzhen in June 2020.

My research interests include Weakly Supervised Learning and Video Generation.

Publications

Mingxiang Liao, Hannan Lu, Xinyu Zhang, Fang Wan, Tianyu Wang, Yuzhong Zhao, Wangmeng Zuo, Qixiang Ye, Jingdong Wang
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective"

[Paper] [Code]
Mingxiang Liao, Fang Wan, Zonghao Guo, Qixiang Ye
Hierarchical AttentionShift for Pointly Supervised Instance Segmentation"
Submitted to TNNLS
Mingxiang Liao, Zonghao Guo, Yuze Wang, Bailan Feng, Peng Yuan, Fang Wan
AttentionShift: Iteratively Estimated Part-based Attention Map for Pointly Supervised Instance Segmentation"
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2023)
[Paper]
Mingxiang Liao, Fang Wan, Yuan Yao, Zhenjun Han, Jialing Zou, Yuze Wang, Bailan Feng, Peng Yuan, Qixiang Ye
End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution
2022 European Conference on Computer Vision (ECCV2022)
[Paper] [Code]


Statistics