Abstract

A common trend in object recognition is to detect and leverage the use of sparse, informative feature points. The use of such features makes the problem more manageable while providing increased robustness to noise and pose variation. In this work we develop an extension of these ideas to the spatio-temporal case. For this purpose, we show that the direct 3D counterparts to commonly used 2D interest point detectors are inadequate, and we propose an alternative. Anchoring off of these interest points, we devise a recognition algorithm based on spatio-temporally windowed data. We present recognition results on a variety of datasets including both human and rodent behavior.

Keywords

Computer scienceRobustness (evolution)Artificial intelligenceLeverage (statistics)Pattern recognition (psychology)Cognitive neuroscience of visual object recognitionFeature extraction

Affiliated Institutions

Related Publications

Publication Info

Year
2006
Type
article
Pages
65-72
Citations
2463
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

2463
OpenAlex

Cite This

Piotr Dollár, Vincent Rabaud, Garrison W. Cottrell et al. (2006). Behavior Recognition via Sparse Spatio-Temporal Features. , 65-72. https://doi.org/10.1109/vspets.2005.1570899

Identifiers

DOI
10.1109/vspets.2005.1570899