Elastic Functional Coding of Riemannian Trajectories

by   Rushil Anirudh, et al.

Visual observations of dynamic phenomena, such as human actions, are often represented as sequences of smoothly-varying features . In cases where the feature spaces can be structured as Riemannian manifolds, the corresponding representations become trajectories on manifolds. Analysis of these trajectories is challenging due to non-linearity of underlying spaces and high-dimensionality of trajectories. In vision problems, given the nature of physical systems involved, these phenomena are better characterized on a low-dimensional manifold compared to the space of Riemannian trajectories. For instance, if one does not impose physical constraints of the human body, in data involving human action analysis, the resulting representation space will have highly redundant features. Learning an effective, low-dimensional embedding for action representations will have a huge impact in the areas of search and retrieval, visualization, learning, and recognition. The difficulty lies in inherent non-linearity of the domain and temporal variability of actions that can distort any traditional metric between trajectories. To overcome these issues, we use the framework based on transported square-root velocity fields (TSRVF); this framework has several desirable properties, including a rate-invariant metric and vector space representations. We propose to learn an embedding such that each action trajectory is mapped to a single point in a low-dimensional Euclidean space, and the trajectories that differ only in temporal rates map to the same point. We utilize the TSRVF representation, and accompanying statistical summaries of Riemannian trajectories, to extend existing coding methods such as PCA, KSVD and Label Consistent KSVD to Riemannian trajectories or more generally to Riemannian functions.


page 1

page 2

page 7

page 10

page 12


Video-Based Action Recognition Using Rate-Invariant Analysis of Covariance Trajectories

Statistical classification of actions in videos is mostly performed by e...

Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

Riemannian manifolds have been widely employed for video representations...

4D Atlas: Statistical Analysis of the Spatiotemporal Variability in Longitudinal 3D Shape Data

We propose a novel framework to learn the spatiotemporal variability in ...

On the Vector Space in Photoplethysmography Imaging

We study the vector space of visible wavelength intensities from face vi...

Exploring Visual Patterns in Projected Human and Machine Decision-Making Paths

In problem solving, the paths towards solutions can be viewed as a seque...

Expected path length on random manifolds

Manifold learning seeks a low dimensional representation that faithfully...

Directed Graph Embeddings in Pseudo-Riemannian Manifolds

The inductive biases of graph representation learning algorithms are oft...

Please sign up or login with your details

Forgot password? Click here to reset