Q
Qiong Cao
Researcher at Tencent
Publications - 24
Citations - 3084
Qiong Cao is an academic researcher from Tencent. The author has contributed to research in topics: Metric (mathematics) & Facial recognition system. The author has an hindex of 10, co-authored 21 publications receiving 2077 citations. Previous affiliations of Qiong Cao include University of Exeter & University of Oxford.
Papers
More filters
Proceedings ArticleDOI
VGGFace2: A Dataset for Recognising Faces across Pose and Age
TL;DR: VGGFace2 as discussed by the authors is a large-scale face dataset with 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject.
Proceedings ArticleDOI
Similarity Metric Learning for Face Recognition
Qiong Cao,Yiming Ying,Peng Li +2 more
TL;DR: This paper develops a novel regularization framework to learn similarity metrics for unconstrained face verification by incorporating the robustness to the large intra-personal variations and the discriminative power of novel similarity metrics.
Posted Content
Generalization Bounds for Metric and Similarity Learning
TL;DR: The novel generalization analysis develops and refines the techniques of U-statistics and Rademacher complexity analysis and indicates that sparse metric/similarity learning with $$L^1$$L1-norm regularization could lead to significantly better bounds than those with Frobenius- norm regularization.
Proceedings ArticleDOI
Template Adaptation for Face Verification and Identification
TL;DR: In this article, the authors study the problem of template adaptation, a form of transfer learning to the set of media in a template, and show that perhaps the simplest method of template adaption, combining deep convolutional network features with template specific linear SVMs, outperforms the state-of-the-art by a wide margin.
Journal ArticleDOI
Generalization bounds for metric and similarity learning
TL;DR: In this paper, the generalization analysis of metric and similarity learning is reduced to the estimation of the Rademacher average over "sums-of-iid" sample-blocks related to the specific matrix norm.