Multi-channel correlation filters for human action recognition

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 represented as a multi-channel signal (frames) and the goal is to learn a multi-channel filter for each action class that prod...

Full description

Saved in:
Bibliographic Details
Published in2014 IEEE International Conference on Image Processing (ICIP) pp. 1485 - 1489
Main Authors Kiani, Hamed, Sim, Terence, Lucey, Simon
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Action recognition
Correlation
Correlation filters
Equations
Frequency-domain analysis
Lifting equipment
Multi-channel features
Testing
Training
Videos
Online AccessGet full text

Cover

More Information
Summary: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 represented as a multi-channel signal (frames) and the goal is to learn a multi-channel filter for each action class that produces 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.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2014.7025297