A Compact Kernel Approximation for 3D Action Recognition

by   Jacopo Cavazza, et al.

3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm for 3D action recognition, yielding state-of-the-art results. Yet, the whole framework is affected by the well-known scalability issue. In fact, in general, the kernel function has to be evaluated for all pairs of instances inducing a Gram matrix whose complexity is quadratic in the number of samples. In this work we reduce such complexity to be linear by proposing a novel and explicit feature map to approximate the kernel function. This allows to train a linear classifier with an explicit feature encoding, which implicitly implements a Log-Euclidean machine in a scalable fashion. Not only we prove that the proposed approximation is unbiased, but also we work out an explicit strong bound for its variance, attesting a theoretical superiority of our approach with respect to existing ones. Experimentally, we verify that our representation provides a compact encoding and outperforms other approximation schemes on a number of publicly available benchmark datasets for 3D action recognition.


page 1

page 2

page 3

page 4


Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines

Despite the recent deep learning (DL) revolution, kernel machines still ...

When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data

Human action recognition from skeletal data is a hot research topic and ...

Kernelized Covariance for Action Recognition

In this paper we aim at increasing the descriptive power of the covarian...

Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition

Recently, infrared human action recognition has attracted increasing att...

Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition

Most action recognition datasets and algorithms assume a closed world, w...

Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories

We propose a feature for action recognition called Trajectory-Set (TS), ...

Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification

This paper presents a novel framework for visual object recognition usin...

Please sign up or login with your details

Forgot password? Click here to reset