Abstract

This paper takes a step forward in image and video coding by extending the well-known Vector of Locally Aggregated Descriptors (VLAD) onto an extensive space of curved Riemannian manifolds. We provide a comprehensive mathematical framework that formulates the aggregation problem of such manifold data into an elegant solution. In particular, we consider structured descriptors from visual data, namely Region Covariance Descriptors and linear subspaces that reside on the manifold of Symmetric Positive Defifinite matrices and the Grassmannian manifolds, respectively. Through rigorous experimental validation, we demonstrate the superior performance of this novel Riemannian VLAD descriptor on several visual classifification tasks including video-based face recognition, dynamic scene recognition, and head pose classifification