Qiang (Irving) Meng
I am currently an algorithm engineer at AiBee working on computer vision including face recognition, image retrieval, car/person re-identification, etc.
I am also a sub-core leader here (i.e., tech leader) leading a group with 5 employees and 2 interns.
I graduated with a master degree in Industrial Engineering from University of Washington, Seattle.
Before that, I received my bachelor degree in Mechanical Engineering from University of Science and Technology of China, with a GPA of 3.78/4.3 (Rank: 3/61).
Curriculum Vitae  |
- 01/2022:    Our Paper "Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters" was accepted by ICLR 2022 as a spotlight paper.
- 01/2022:    Publish the paper "Basket-based Softmax" on arXiv (a work done in 2020.11) .
- 11/2021:    Invited talk in the workshop on face image quality organized by EAB, DHS-OBIM, NIST, eu-LISA, etc.
- 07/2021:    Our paper "Learning Compatible Embeddings" was accepted by ICCV 2021.
- 07/2021:    Publish the paper "PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition" on arXiv (a work done in 2020.3) .
- 06/2021:    Invited talk about MagFace in 机器之心.
- 03/2021:    Our paper "MagFace: A Universal Representation for Face Recognition and Quality Assessment" was accepted by CVPR 2021 as an oral paper.
- 12/2020:    Our paper "Searching for Alignment in Face Recognition" was accepted by AAAI 2021.
- 08/2018:    Got my master degree :), but quit the PhD program :(.
- 06/2015:    Got my bachelor degree.
My research interests lie in computer vision, optimization and privacy protection.
Representative works are highlighted.
Qiang Meng, Guxin Qian, Xiaqing Xu, Feng Zhou
A simple but effective mining-during-traning strategy which trains models on multiple datasets in an end-to-end fashion.
PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition
Qiang Meng, Xiaqing Xu, Xiaobo Wang, Yang Qian, Yunxiao Qin, Zezheng Wang, Chenxu Zhao, Feng Zhou, Zhen Lei
An efficient large-pose face recognition method which utilizes the facial landmarks to disentangle the pose-invariant features and exploits a pose-adaptive loss to handle the imbalance issue adaptively.
Searching for Alignment in Face Recognition
Xiaqing Xu, Qiang Meng,
Yunxiao Qin, Jianzhu Guo, Chenxu Zhao, Feng Zhou, Zhen Lei
We design a face template searching space with decomposed crop size and vertical shift, and propose the Face Alignment Policy Search (FAPS) to find optimal alignment templates for face recognition.