Enhancing Action Recognition by Cross-Domain Dictionary Learning

We present a novel cross-dataset action recognition framework that utilizes relevant actions from other visual domains as auxiliary knowledge for enhancing the learning system in the target domain. The data distribution of relevant actions from a source dataset is adapted to match the data distribution of actions in the target dataset via a cross-domain discriminative dictionary learning method, through which a reconstructive, discriminative and domain-adaptive dictionary-pair can be learned. Using selected categories from the HMDB51 dataset as the source domain actions, the proposed framework achieves outstanding performance on the UCF YouTube dataset.