Multiple Kernel Learning for Emotion Recognition in the Wild

We propose a method to automatically detect emotions in unconstrained settings as part of the 2013 Emotion Recog-nition in the Wild Challenge [16], organized in conjunction with the ACM International Conference on Multimodal In-teraction (ICMI 2013). Our method combines multiple vi-sual descriptors with paralinguistic audio features for mul-timodal classification of video clips. Extracted features are combined using Multiple Kernel Learning and the clips are classified using an SVM into one of the seven emotion cat