Abstract:
Localizing facial landmarks is a fundamental step in facial image analysis. However, the problem continues to be challenging in condition of large variations caused by po...Show MoreMetadata
Abstract:
Localizing facial landmarks is a fundamental step in facial image analysis. However, the problem continues to be challenging in condition of large variations caused by pose disparity, illumination, expression and occlusion. In this paper, we propose a coarse-to-fine framework which joints stacked hourglass network and salient region attention refinement for robust face alignment. To achieve this, we firstly develop a multi-scale region learning module (MSL) to analyze the structure and texture information at different facial region and extract strong discriminative deep feature. Then we employ a novel convolutional neural network named stacked hourglass network (SHN) for heatmap regression and initial facial landmarks prediction. Moreover, we present a salient region attention module (SRA) to extract precise feature based on the heatmap regression, and the filtered feature is used for landmarks refinement. The extensive experimental results on two public datasets, including 300W and COFW, confirm the validity of our model.
Published in: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
Date of Conference: 14-18 May 2019
Date Added to IEEE Xplore: 11 July 2019
ISBN Information:
Stack of Heatmap Hourglass Network for Face Alignment
Athman Dhiya Abdulsatar,Ali Mohsin Aljuboori
ARFNet: Attention-Oriented Refinement and Fusion Network for Light Field Salient Object Detection
Shuai Ma,Licheng Zhu,Xianfeng Chen,Xu Yan,Shuai Wang,Ping Yang,Bing Xu
Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks
Keqiang Li,Huaiyu Wu,Xiuqin Shang,Zhen Shen,Gang Xiong,Xisong Dong,Bin Hu,Fei-Yue Wang
Learning Deformable Hourglass Networks (DHGN) for Unconstrained Face Alignment
Jiaqiang Zhang,Congcong Zhu,Suping Wu,Zhenhua Yu,Xuehong Sun,Hao Liu
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
Kaipeng Zhang,Zhanpeng Zhang,Zhifeng Li,Yu Qiao
Region-Based Context Enhanced Network for Robust Multiple Face Alignment
Xuxin Lin,Yanyan Liang,Jun Wan,Chi Lin,Stan Z. Li
Attention-Guided Coarse-to-Fine Network for 2D Face Alignment in the Wild
Xin Liu,Huabin Wang,Jian Zhou,Liang Tao
Face Alignment by Combining Residual Features in Cascaded Hourglass Network
Weiliang Chen,Qiang Zhou,Roland Hu
Improving Face Recognition for Smart Home Security: A Study of Resnet, Siamese Networks, and Attention Mechanisms
Hemaang Sood,B.V.S Nikhil,Palak Dengla,Sanya Saeed,Nagabhushan SV
Dual-Path Adaptive Channel Attention Network Based on Feature Constraints for Face Anti-Spoofing
Nana Li,Zhipeng Weng,Fangmei Liu,Zuhe Li,Wei Wang