Despite significant successes achieved in knowledge discovery, traditional machine
learning methods may fail to obtain satisfactory performances when dealing with complex …

Ensemble learning is a prolific field in Machine Learning since it is based on the assumption
that combining the output of multiple models is better than using a single model, and it …

Artificial neural networks have been successfully applied to a variety of machine learning
tasks, including image recognition, semantic segmentation, and machine translation …

This paper describes our approach towards robust facial expression recognition (FER) for
the third Emotion Recognition in the Wild (EmotiW2015) challenge. We train multiple deep …

To perform unconstrained face recognition robust to variations in illumination, pose and
expression, this paper presents a new scheme to extract “Multi-Directional Multi-Level Dual …

By coding the input testing image as a sparse linear combination of the training samples via
l 1-norm minimization, sparse representation based classification (SRC) has been recently …

Gabor features have been known to be effective for face recognition. However, only a few
approaches utilize phase feature and they usually perform worse than those using …

Regularized linear representation learning has led to interesting results in image
classification, while how the object should be represented is a critical issue to be …

Illumination preprocessing is an effective and efficient approach in handling lighting
variations for face recognition. Despite much attention to face illumination preprocessing …

We present a pattern recognition framework to improve committee machines of deep
convolutional neural networks (deep CNNs) and its application to static facial expression …