Kernelized covariance for action recognition

By Jacopo Cavazza, Andrea Zunino, Marco San-Biagio, Vittorio Murino. 2016

47 citations recorded by the source corpus.

In this paper we aim at increasing the descriptive power of the covariance matrix, limited in capturing linear mutual dependencies between variables only. We present a rigorous and principled mathematical pipeline to recover the kernel trick for computing the covariance matrix, enhancing it to model more complex, non-linear relationships conveyed by the raw data. To this end, we propose Kernelized-COV, which generalizes the original covariance representation without compromising the efficiency of the computation. In the experiments, we validate the proposed framework against many previous approaches in the literature, scoring on par or superior with respect to the state of the art on benchmark datasets for 3D action recognition.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “ Complexity column: Real-Time. Dataset Ref. Approach Modality Feature Encoding Structure & Transition Feature Engineering Precision (%) Complexity MSR Action3D [221] Ker-RP M Stat Lowlv Hand 96.9 [206] Kernelized-COV P Stat Lowlv Hand 96.2 [218] Angle & Moving Pose M BoW Lowlv Unsup 96.1 RT ”
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “The reason for this lies in the statistical computation of second order temporal momentum of Pa, the latter being very discriminative in recognizing human actions [16, 37, 3].”
Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (2016, methodology): “Kernel trick was utilized for action recognition in kernelized covariances [24] which are obtained in Nyström-like process.”