Statistics of Pairwise Co-occurring Local Spatio-Temporal Features for Human Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Statistics of Pairwise Co-occurring Local Spatio-Temporal 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 in videos. Together these techniques have demonstrated high recognition results for a number of action classes. Recent approaches have typically focused on capturing global statistics of features. However, existing methods ignore relations between features and thus may not be discriminative enough. Therefore, we propose a novel feature representation which captures statistics of pairwise co-occurring local spatio-temporal features. Our representation captures not only global distribution of features but also focuses on geometric and appearance (both visual and motion) relations among the features. Calculating a set of bag-of-words representations with different geometrical arrangement among the features, we keep an important association between appearance and geometric information. Using two benchmark datasets for human action recognition, we demonstrate that our representation enhances the discriminative power of features and improves action recognition performance.
Fichier principal
Vignette du fichier
Statistics_of_Pairwise_Co-occurring_Local_Spatio-Temporal_Features_for_Human_Action_Recognition.pdf (327.87 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00760963 , version 1 (04-12-2012)

Identifiers

Cite

Piotr Bilinski, Francois Bremond. Statistics of Pairwise Co-occurring Local Spatio-Temporal Features for Human Action Recognition. 4th International Workshop on Video Event Categorization, Tagging and Retrieval (VECTaR), in conjunction with 12th European Conference on Computer Vision (ECCV), Oct 2012, Florence, Italy. pp.311-320, ⟨10.1007/978-3-642-33863-2_31⟩. ⟨hal-00760963⟩

Collections

INRIA INRIA2
164 View
268 Download

Altmetric

Share

Gmail Facebook X LinkedIn More