Action Recognition and Localization by Hierarchical Space-Time Segments

Shugao Ma, Jianming Zhang, Nazli Ikizler-Cinbis, Stan Sclaroff; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2744-2751

Abstract


We propose Hierarchical Space-Time Segments as a new representation for action recognition and localization. This representation has a two-level hierarchy. The first level comprises the root space-time segments that may contain a human body. The second level comprises multi-grained space-time segments that contain parts of the root. We present an unsupervised method to generate this representation from video, which extracts both static and non-static relevant space-time segments, and also preserves their hierarchical and temporal relationships. Using simple linear SVM on the resultant bag of hierarchical space-time segments representation, we attain better than, or comparable to, state-of-the-art action recognition performance on two challenging benchmark datasets and at the same time produce good action localization results.

Related Material


[pdf]
[bibtex]
@InProceedings{Ma_2013_ICCV,
author = {Ma, Shugao and Zhang, Jianming and Ikizler-Cinbis, Nazli and Sclaroff, Stan},
title = {Action Recognition and Localization by Hierarchical Space-Time Segments},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}