Ordinal loss is widely used in solving regression problems with deep learning technologies. Its basic idea to convert classification while preserving the natural order. However, order constraint enforced only by ordinal label implicitly, leading real output values not strictly It causes network learn separable feature rather than discriminative feature, and possibly overfit on training set. In ...

In this paper,wepropose a supervised SmoothMulti-Manifold Embedding (SMME) method for robust identity-independent head pose estimation. In order to handle the appearance variations caused by identity, we consider the pose data space as multiple manifolds in which each manifold characterizes the underlying subspace of subjects with similar appearance. We then propose a novel embedding criterion ...

Pose estimation is an important part in human face recognition because head rotations will significantly affect the recognition accuracy. However, automated and accurate pose determination still remains an unsolved problem in the research community. In this paper, we propose a novel Elastic Energy Model to tackle this problem, which employs statistical energy contributions of a set of feature p...

Automatic estimation of head pose from a face image is a sub-problem of human face analysis with widespread applications such as gaze direction detection, human computer interaction or video teleconferencing. It can also be integrated in a multi-view face detection and recognition system. Current methods on face pose estimation from a 2D image can be divided into two groups. The first group : g...