Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction. This emerging technique has reshaped the research …
G Guo, N Zhang - Computer vision and image understanding, 2019 - Elsevier
Deep learning, in particular the deep convolutional neural networks, has received increasing interests in face recognition recently, and a number of deep learning methods …
S Liu, T Li, W Chen, H Li - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning …
L Tran, X Yin, X Liu - … of the IEEE conference on computer …, 2017 - openaccess.thecvf.com
The large pose discrepancy between two face images is one of the key challenges in face recognition. Conventional approaches for pose-invariant face recognition either perform …
X Yin, X Yu, K Sohn, X Liu… - Proceedings of the …, 2019 - openaccess.thecvf.com
Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such …
We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss …
X Zhu, X Liu, Z Lei, SZ Li - IEEE transactions on pattern …, 2017 - ieeexplore.ieee.org
Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in the computer vision community. However, most …
In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks (DCNNs). A typical pipeline for face verification includes …
X Wang, L Bo, L Fuxin - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely …