E
Erjin Zhou
Researcher at Tsinghua University
Publications - 23
Citations - 2335
Erjin Zhou is an academic researcher from Tsinghua University. The author has contributed to research in topics: Facial recognition system & Convolutional neural network. The author has an hindex of 14, co-authored 21 publications receiving 1968 citations.
Papers
More filters
Proceedings ArticleDOI
Going Deeper with Embedded FPGA Platform for Convolutional Neural Network
Jiantao Qiu,Jie Wang,Song Yao,Kaiyuan Guo,Boxun Li,Erjin Zhou,Jincheng Yu,Tianqi Tang,Ningyi Xu,Sen Song,Yu Wang,Huazhong Yang +11 more
TL;DR: This paper presents an in-depth analysis of state-of-the-art CNN models and shows that Convolutional layers are computational-centric and Fully-Connected layers are memory-centric, and proposes a CNN accelerator design on embedded FPGA for Image-Net large-scale image classification.
Proceedings ArticleDOI
Extensive Facial Landmark Localization with Coarse-to-Fine Convolutional Network Cascade
TL;DR: A four-level convolutional network cascade that is trained to locally refine a subset of facial landmarks generated by previous network levels, which enables the system to locate extensive facial landmarks accurately in the 300-W facial landmark localization challenge.
Posted Content
Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
Erjin Zhou,Zhimin Cao,Qi Yin +2 more
TL;DR: The Megvii Face Recognition System is built, which achieves 99.50% accuracy on the LFW benchmark, outperforming the previous state-of-the-art, and the performance in a real-world security certification scenario is reported.
Proceedings Article
Learning face hallucination in the wild
TL;DR: A new method of face hallucination is presented, which can consistently improve the resolution of face images even with large appearance variations, based on a novel network architecture called Bi-channel Convolutional Neural Network (Bi-channel CNN).
Journal ArticleDOI
Approaching human level facial landmark localization by deep learning
Haoqiang Fan,Erjin Zhou +1 more
TL;DR: The solution to the 300 Faces in the Wild Facial Landmark Localization Challenge is presented, and how to achieve very competitive localization performance with a simple deep learning based system is demonstrated.