Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/22783
Title: Structure context of local features in realistic human action recognition
Authors: Wu, Q
Lu, S
Wang, Z
Deng, F
Kang, W
Feng, DD
Keywords: Feature extraction
Image recognition
Support vector machines
Video signal processing
Issue Date: 2011
Publisher: IEEE
Source: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 6-13 November 2011, Barcelona, p. 1496-1501 How to cite?
Abstract: Realistic human action recognition has been emerging as a challenging research topic due to the difficulties of representing different human actions in diverse realistic scenes. In the bag-of-features model, human actions are generally represented with the distribution of local features derived from the keypoints of action videos. Various local features have been proposed to characterize those key points. However, the important structural information among the key points has not been well investigated yet. In this paper, we propose to characterize such structure information with shape context. Therefore, each keypoint is characterized with both its local visual attributes and its global structural context contributed by other keypoints. The bag-of-features model is utilized for representing each human action and SVM is employed to perform human action recognition. Experimental results on the challenging YouTube dataset and HOHA-2 dataset demonstrate that our proposed approach accounting for structural information is more effective in representing realistic human actions. In addition, we also investigate the impact of choosing different local features such as SIFT, HOG, and HOF descriptors in human action representation. It is observed that dense keypoints can better exploit the advantages of our proposed approach.
URI: http://hdl.handle.net/10397/22783
ISBN: 978-1-4673-0062-9
DOI: 10.1109/ICCVW.2011.6130427
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Last Week
0
Last month
Citations as of Oct 2, 2017

Page view(s)

32
Last Week
2
Last month
Checked on Oct 16, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.