37 citations · 78 across the 7 of their papers we have counts for
7 papers
Towards Privacy-Preserving, Real-Time and Lossless Feature Matching
Qiang Meng, Feng Zhou
Most visual retrieval applications store feature vectors for downstream matching tasks. These vectors, from where user information can be spied out, will cause privacy leakage if n…
Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters
Qiang Meng, Feng Zhou, Hainan Ren +3
The growing public concerns on data privacy in face recognition can be greatly addressed by the federated learning (FL) paradigm. However, conventional FL methods perform poorly du…
Basket-based Softmax
Qiang Meng, Xinqian Gu, Xiaqing Xu +1
Softmax-based losses have achieved state-of-the-art performances on various tasks such as face recognition and re-identification. However, these methods highly relied on clean data…
Learning Compatible Embeddings
Qiang Meng, Chixiang Zhang, Xiaoqiang Xu +1
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieva…
PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition
Qiang Meng, Xiaqing Xu, Xiaobo Wang +6
Despite the great success achieved by deep learning methods in face recognition, severe performance drops are observed for large pose variations in unconstrained environments (e.g.…
Searching for Alignment in Face Recognition
Xiaqing Xu, Qiang Meng, Yunxiao Qin +4
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the…
MagFace: A Universal Representation for Face Recognition and Quality Assessment
Qiang Meng, Shichao Zhao, Zhida Huang +1
The performance of face recognition system degrades when the variability of the acquired faces increases. Prior work alleviates this issue by either monitoring the face quality in…