Temporal causality for the analysis of visual events

We present a novel approach to the causal temporal analysis of event data from video content. Our key observation is that the sequence of visual words produced by a space-time dictionary representation of a video sequence can be interpreted as a multivariate point-process. By using a spectral versio...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 1967 - 1974
Main Authors Prabhakar, Karthir, Sangmin Oh, Ping Wang, Abowd, Gregory D, Rehg, James M
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2010
Subjects
Brain modeling
Data analysis
Dictionaries
Games
Motion analysis
Performance analysis
Space technology
Testing
Video sequences
Vocabulary
Online AccessGet full text

Cover

More Information
Summary:We present a novel approach to the causal temporal analysis of event data from video content. Our key observation is that the sequence of visual words produced by a space-time dictionary representation of a video sequence can be interpreted as a multivariate point-process. By using a spectral version of the pairwise test for Granger causality, we can identify patterns of interactions between words and group them into independent causal sets. We demonstrate qualitatively that this produces semantically-meaningful groupings, and we demonstrate quantitatively that these groupings lead to improved performance in retrieving and classifying social games from unstructured videos.
ISBN:1424469848
9781424469840
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2010.5539871