Contextual Statistics of Space-Time Ordered Features for Human Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Contextual Statistics of Space-Time Ordered Features for Human Action Recognition

Abstract

The bag-of-words approach with local spatio-temporal features have become a popular video representation for action recognition. Recent methods have typically focused on capturing global and local statistics of features. However, existing approaches ignore relations between the features, particularly space-time arrangement of features, and thus may not be discriminative enough. Therefore, we propose a novel figure-centric representation which captures both local density of features and statistics of space-time ordered features. Using two benchmark datasets for human action recognition, we demonstrate that our representation enhances the discriminative power of features and improves action recognition performance, achieving 96.16% recognition rate on popular KTH action dataset and 93.33% on challenging ADL dataset.
Fichier principal
Vignette du fichier
Contextual_Statistics_of_Space-Time_Ordered_Features_for_Human_Action_Recognition.pdf (223.24 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00718293 , version 1 (16-07-2012)

Identifiers

  • HAL Id : hal-00718293 , version 1

Cite

Piotr Bilinski, Francois Bremond. Contextual Statistics of Space-Time Ordered Features for Human Action Recognition. 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), Sep 2012, Beijing, China. ⟨hal-00718293⟩

Collections

INRIA INRIA2
185 View
331 Download

Share

Gmail Facebook X LinkedIn More