output
20182026
most citedMobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

48 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2018Show all

2 papers · 1 filter

cs.CV2018

Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate

Sheng Chen, Jia Guo, Yang Liu +2

In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 no…

cs.CV2018★ 48 cited

MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

Sheng Chen, Yang Liu, Xiang Gao +1

We present a class of extremely efficient CNN models, MobileFaceNets, which use less than 1 million parameters and are specifically tailored for high-accuracy real-time face verifi…