Action Recognition by Multiple Features and Hyper-Sphere Multi-class SVM
- 1 August 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2010 20th International Conference on Pattern Recognition
- p. 3744-3747
- https://doi.org/10.1109/icpr.2010.912
Abstract
In this paper we propose a novel framework for action recognition based on multiple features for improve action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single feature based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc.). Hence, we use two kinds of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (cuboids and 2-D SIFT), and ii) the higher-order statistical models of interest points, which aims to capture the global information of the actor. We construct video representation in terms of local space-time features and global features and integrate such representations with hyper-sphere multi-class SVM. Experiments on publicly available datasets show that our proposed approach is effective. An additional experiment shows that using both local and global features provides a richer representation of human action when compared to the use of a single feature type.Keywords
This publication has 8 references indexed in Scilit:
- Recognising action as clouds of space-time interest pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Action snippets: How many frames does human action recognition require?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Action recognition with motion-appearance vocabulary forestPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Actions as Space-Time ShapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Extracting Spatiotemporal Interest Points using Global InformationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Behavior Recognition via Sparse Spatio-Temporal FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004