Original paper
Facial Landmark Detection with Tweaked Convolutional Neural Networks
Volume: 40, Issue: 12, Pages: 3067 - 3074
Published: Dec 25, 2017
Abstract
This paper concerns the problem of facial landmark detection. We provide a unique new analysis of the features produced at intermediate layers of a convolutional neural network (CNN) trained to regress facial landmark coordinates. This analysis shows that while being processed by the CNN, face images can be partitioned in an unsupervised manner into subsets containing faces in similar poses (i.e., 3D views) and facial properties (e.g., presence...
Paper Details
Title
Facial Landmark Detection with Tweaked Convolutional Neural Networks
Published Date
Dec 25, 2017
Volume
40
Issue
12
Pages
3067 - 3074