Collaborative Sparse Coding for Multiview Action Recognition

Multiview action recognition has received increasing attention over the past decade. Various approaches have been proposed to extract view-invariant features; among them, self-similarity matrices (SSMs) have shown outstanding performance. However, SSMs become sensitive when there's a very large view change. To make SSMs more robust to viewpoint changes, the authors propose a collaborative sparse coding framework. They integrate the classifier training process and sparse coding process into a unified collaborative filtering framework; this lets more discriminative sparse video representations and classifiers be learned by optimizing the dictionary and classifier jointly. Experimental results demonstrate the effectiveness of the framework.