Event Location: NSH 1507

Abstract: The popular bag-of-words paradigm for action recognition tasks is based on
building histograms of quantized features, typically at the cost of
discarding all information about relationships between them. However,
although the beneficial nature of including these relationships seems
obvious, in practice finding good representations for feature
relationships in video is difficult. We propose a simple and
computationally efficient method for expressing pairwise relationships
between quantized features that combines key aspects of Naive Bayes
inspired and discriminative representations. We demonstrate how our
technique can augment both appearance- and motion-based features, and that
this augmentation significantly improves performance on both types of
features on several video datasets.