Despite the recent deep learning (DL) revolution, kernel machines still remain powerful methods for action recognition. DL has brought the use of large datasets and this is typically a problem for kernel approaches, which are not scaling up eciently due to kernel Gram matrices. Nevertheless, kernel methods are still attractive and more generally applicable since they can equally manage dierent sizes of the datasets, also in cases where DL techniques show some limitations. This work investigates these issues by proposing an explicit ap- proximated representation that, together with a linear model, is an equivalent, yet scalable, implementation of a kernel machine. Our approximation is directly inspired by the exact feature map that is induced by an RBF Gaussian kernel but, unlike the latter, it is nite dimensional and very compact. We justify the soundness of our idea with a theoretical analysis which proves the unbiasedness of the approximation, and provides a vanishing bound for its variance, which is shown to decrease much rapidly than in alternative methods in the literature. In a broad experimental validation, we assess the superiority of our approximation in terms of 1) ease and speed of training, 2) compactness of the model, and 3) improvements with respect to the state-of-the-art performance.

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

V. Murino
Supervision
2019-01-01

Abstract

Despite the recent deep learning (DL) revolution, kernel machines still remain powerful methods for action recognition. DL has brought the use of large datasets and this is typically a problem for kernel approaches, which are not scaling up eciently due to kernel Gram matrices. Nevertheless, kernel methods are still attractive and more generally applicable since they can equally manage dierent sizes of the datasets, also in cases where DL techniques show some limitations. This work investigates these issues by proposing an explicit ap- proximated representation that, together with a linear model, is an equivalent, yet scalable, implementation of a kernel machine. Our approximation is directly inspired by the exact feature map that is induced by an RBF Gaussian kernel but, unlike the latter, it is nite dimensional and very compact. We justify the soundness of our idea with a theoretical analysis which proves the unbiasedness of the approximation, and provides a vanishing bound for its variance, which is shown to decrease much rapidly than in alternative methods in the literature. In a broad experimental validation, we assess the superiority of our approximation in terms of 1) ease and speed of training, 2) compactness of the model, and 3) improvements with respect to the state-of-the-art performance.
2019
Kernel Machines, Kernel Approximation, Action Recognition, Skeletal Joints, Covariance Representation
File in questo prodotto:
File Dimensione Formato  
kronapprox-PR.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Dominio pubblico
Dimensione 661.25 kB
Formato Adobe PDF
661.25 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1033271
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact