Xiaolong Liu
PhD Candidate
China
Summary
👤
SeniorXiaolong Liu is a Principal Engineer and PhD in computer vision based in Wuhan with a decade of experience focused on deep learning for video understanding, particularly action recognition and detection. He has five first-author publications, including three at CVPR/TIP, and led research internships at Alibaba and Megvii that produced top-tier papers, patents, and a Tianchi competition on temporal event localization. Since December 2022 he has been applying his research skills at Huawei, transitioning academic advances into real-world systems. Known for bridging rigorous academic work with industrial impact, he combines strong publication pedigree and practical engineering to tackle long-video understanding problems. Outside publications, his homepage and GitHub reflect active work on reproducible CV research and tooling for large-scale video tasks.
10 years of coding experience
Github Skills (22)
temporal9
video-understanding8
benchmark7
action-recognition7
localization7
segment7
weakly-supervised-learning6
deep-learning5
pytorch5
self-attention4
recurrent4
action-localization4
computer-vision4
unsupervised-learning3
vision-transformer3
Programming languages (2)
Github contributions (5)
xlliu7/TadTR
Jun 2021 - Oct 2022
Contributions:18 commits, 18 pushes, 1 branch in 1 year 5 months
xlliu7/MUSES
Dec 2020 - Mar 2022
Code for the paper "Multi-shot Temporal Event Localization: a Benchmark", CVPR 2021
Contributions:12 commits, 12 pushes, 15 comments in 1 year 3 months
pytorchdeep-learningtemporalbenchmarkcvpr
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.