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
9th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), Sep 2012, Beijing, China. 2012
Liste complète des métadonnées


https://hal.inria.fr/hal-00718293
Contributor : Piotr Bilinski <>
Submitted on : Monday, July 16, 2012 - 3:46:20 PM
Last modification on : Monday, October 5, 2015 - 5:01:44 PM
Document(s) archivé(s) le : Wednesday, October 17, 2012 - 2:46:25 AM

File

Contextual_Statistics_of_Space...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00718293, version 1

Collections

Citation

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. 2012. <hal-00718293>

Share

Metrics

Record views

256

Document downloads

246