Abstract

Retrieving videos of a specifific person given his/her face image as query becomes more and more appealing for applications like smart movie fast-forwards and suspect searching. It also forms an interesting but challenging computer vision task, as the visual data to match, i.e., still image and video clip are usually represented quite differently. Typically, face image is represented as point (i.e., vector) in Euclidean space, while video clip is seemingly modeled as a point (e.g., covariance matrix) on some particular Riemannian manifold in the light of its recent promising success. It thus incurs a new hashing-based retrieval problem of matching two heterogeneous representations, respectively in Euclidean space and Riemannian manifold. This work makes the fifirst attempt to embed the two heterogeneous spaces into a common discriminant Hamming space. Specififi- cally, we propose Hashing across Euclidean space and Riemannian manifold (HER) by deriving a unifified framework to fifirstly embed the two spaces into corresponding reproducing kernel Hilbert spaces, and then iteratively optimize the intra- and inter-space Hamming distances in a maxmargin framework to learn the hash functions for the two spaces. Extensive experiments demonstrate the impressive superiority of our method over the state-of-the-art competitive hash learning methods.