Facial Landmark Detection with Tweaked Convolutional Neural Networks.
IEEE Transactions on Pattern Analysis and Machine Intelligence（2018）
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.,...更多
Face recognition,Neural networks,Feature extraction,Magnetic heads,Training data,Gesture recognition