The Community for Technology Leaders
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
ISSN: 2160-7516
ISBN: 978-1-4673-6758-5
pp: 22-29
Mohammad Ali Bagheri , Faculty of Computer Science, Dalhousie University, Halifax, Canada
Qigang Gao , Faculty of Computer Science, Dalhousie University, Halifax, Canada
Sergio Escalera , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Albert Clapes , Computer Vision Center, UAB, Edificio O, Campus UAB, 08193, Bellaterra (Cerdanyola), Barcelona, Spain
Kamal Nasrollahi , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Michael B. Holte , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
Thomas B. Moeslund , Visual Analysis of People (VAP) Laboratory, Rendsburggade 14, 9000 Aalborg, Denmark
ABSTRACT
The performance of different action recognition techniques has recently been studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of action learning techniques, each performing the recognition task from a different perspective. The underlying idea is that instead of aiming a very sophisticated and powerful representation/learning technique, we can learn action categories using a set of relatively simple and diverse classifiers, each trained with different feature set. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a learner on an unseen action recognition scenario. This leads to having a more robust and general-applicable framework. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers' output, showing enhanced performance of the proposed methodology.
INDEX TERMS
Feature extraction, Videos, Trajectory, Histograms, Computer vision, Visualization, Accuracy,
CITATION
Mohammad Ali Bagheri, Qigang Gao, Sergio Escalera, Albert Clapes, Kamal Nasrollahi, Michael B. Holte, Thomas B. Moeslund, "Keep it accurate and diverse: Enhancing action recognition performance by ensemble learning", 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), vol. 00, no. , pp. 22-29, 2015, doi:10.1109/CVPRW.2015.7301332
203 ms
(Ver 3.3 (11022016))