October
2014
Multi-Channel Correlation Filters for Human Action Recognition
Authors:
Abstract:
In this work, we propose to employ multi-channel correlation filters for recognizing human actions (e.g. waking, riding) in videos. In our framework, each action sequence is rep- resented as a multi-channel signal (frames) and the goal is to learn a multi-channel filter for each action class that pro- duces a set of desired outputs when correlated with training examples. The experiments on the Weizmann and UCF sport datasets demonstrate superior computational cost (real-time), memory efficiency and very competitive performance of our approach compared to the state of the arts.
copied = false, 2000);
">
@conference{Kiani-2014-17153,
author = {Hamed Kiani And Simon Lucey And Terence Sim},
title = {Multi-Channel Correlation Filters for Human Action Recognition},
booktitle = {Proceedings of IEEE International Conference on Image Processing (ICIP '14)},
year = {2014},
month = {October},
pages = {1485 - 1489},
keywords = {Action recognition, Correlation filters, Multi-channel features},
}
author = {Hamed Kiani And Simon Lucey And Terence Sim},
title = {Multi-Channel Correlation Filters for Human Action Recognition},
booktitle = {Proceedings of IEEE International Conference on Image Processing (ICIP '14)},
year = {2014},
month = {October},
pages = {1485 - 1489},
keywords = {Action recognition, Correlation filters, Multi-channel features},
}