Skip to Main content Skip to Navigation
Conference papers

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

Piotr Bilinski 1 Francois Bremond 1 
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [36 references]  Display  Hide  Download
Contributor : Piotr Bilinski Connect in order to contact the contributor
Submitted on : Monday, July 16, 2012 - 3:46:20 PM
Last modification on : Saturday, June 25, 2022 - 11:07:52 PM
Long-term archiving on: : Wednesday, October 17, 2012 - 2:46:25 AM


Files produced by the author(s)


  • HAL Id : hal-00718293, version 1



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⟩



Record views


Files downloads