ML Anthology

Temporal Causality for the Analysis of Visual Events

Karthir Prabhakar, Sang Min Oh, Ping Wang, Gregory D. Abowd, James M. Rehg
CVPR 2010 pp. 1967-1974
doi:10.1109/CVPR.2010.5539871 /cvpr/2010/prabhakar2010cvpr-temporal/

Abstract

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.

CVPR Semantic Scholar

Cite

Text

Prabhakar et al. "Temporal Causality for the Analysis of Visual Events." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539871

Markdown

[Prabhakar et al. "Temporal Causality for the Analysis of Visual Events." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/prabhakar2010cvpr-temporal/) doi:10.1109/CVPR.2010.5539871

BibTeX

@inproceedings{prabhakar2010cvpr-temporal,
  title     = {{Temporal Causality for the Analysis of Visual Events}},
  author    = {Prabhakar, Karthir and Oh, Sang Min and Wang, Ping and Abowd, Gregory D. and Rehg, James M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {1967-1974},
  doi       = {10.1109/CVPR.2010.5539871},
  url       = {https://mlanthology.org/cvpr/2010/prabhakar2010cvpr-temporal/}
}