Human Action Recognition under Log-Euclidean Riemannian Metric
نویسندگان
چکیده
This paper presents a new action recognition approach based on local spatio-temporal features. The main contributions of our approach are twofold. First, a new local spatio-temporal feature is proposed to represent the cuboids detected in video sequences. Specifically, the descriptor utilizes the covariance matrix to capture the self-correlation information of the low-level features within each cuboid. Since covariance matrices do not lie on Euclidean space, the Log-Euclidean Riemannian metric is used for distance measure between covariance matrices. Second, the Earth Mover’s Distance (EMD) is used for matching any pair of video sequences. In contrast to the widely used Euclidean distance, EMD achieves more robust performances in matching histograms/distributions with different sizes. Experimental results on two datasets demonstrate the effectiveness of the proposed approach.
منابع مشابه
Assessment of the Log-Euclidean Metric Performance in Diffusion Tensor Image Segmentation
Introduction: Appropriate definition of the distance measure between diffusion tensors has a deep impact on Diffusion Tensor Image (DTI) segmentation results. The geodesic metric is the best distance measure since it yields high-quality segmentation results. However, the important problem with the geodesic metric is a high computational cost of the algorithms based on it. The main goal of this ...
متن کاملTangent Bundle of the Hypersurfaces in a Euclidean Space
Let $M$ be an orientable hypersurface in the Euclidean space $R^{2n}$ with induced metric $g$ and $TM$ be its tangent bundle. It is known that the tangent bundle $TM$ has induced metric $overline{g}$ as submanifold of the Euclidean space $R^{4n}$ which is not a natural metric in the sense that the submersion $pi :(TM,overline{g})rightarrow (M,g)$ is not the Riemannian submersion. In this paper...
متن کاملCross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video
Riemannian manifolds have been widely employed for video representations in visual classification tasks including videobased face recognition. The success mainly derives from learning a discriminant Riemannian metric which encodes the non-linear geometry of the underlying Riemannian manifolds. In this paper, we propose a novel metric learning framework to learn a distance metric across a Euclid...
متن کاملGeodesics and Deformed Pseudo–riemannian Manifolds with Symmetry
There is a general method, applicable in many situations, whereby a pseudo–Riemannian metric, invariant under the action of some Lie group, can be deformed to obtain a new metric whose geodesics can be expressed in terms of the geodesics of the old metric and the action of the Lie group. This method applied to Euclidean space and the unit sphere produces new examples of complete Riemannian metr...
متن کاملFace recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning
Face recognition on large-scale video in the wild is becoming increasingly important due to the ubiquity of video data captured by surveillance cameras, handheld devices, Internet uploads, and other sources. By treating each video as one image set, set-based methods recently have made great success in the field of video-based face recognition. In the wild world, videos often contain extremely c...
متن کامل