Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition
Joint Authors
Wang, Bin
Liu, Yu
Wang, Wei
Xu, Wei
Zhang, Maojun
Source
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-09-29
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Medicine
Information Technology and Computer Science
Abstract EN
We propose a Multiscale Locality-Constrained Spatiotemporal Coding (MLSC) method to improve the traditional bag of features (BoF) algorithm which ignores the spatiotemporal relationship of local features for human action recognition in video.
To model this spatiotemporal relationship, MLSC involves the spatiotemporal position of local feature into feature coding processing.
It projects local features into a sub space-time-volume (sub-STV) and encodes them with a locality-constrained linear coding.
A group of sub-STV features obtained from one video with MLSC and max-pooling are used to classify this video.
In classification stage, the Locality-Constrained Group Sparse Representation (LGSR) is adopted to utilize the intrinsic group information of these sub-STV features.
The experimental results on KTH, Weizmann, and UCF sports datasets show that our method achieves better performance than the competing local spatiotemporal feature-based human action recognition methods.
American Psychological Association (APA)
Wang, Bin& Liu, Yu& Wang, Wei& Xu, Wei& Zhang, Maojun. 2013. Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition. The Scientific World Journal،Vol. 2013, no. 2013, pp.1-11.
https://search.emarefa.net/detail/BIM-1032883
Modern Language Association (MLA)
Wang, Bin…[et al.]. Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition. The Scientific World Journal No. 2013 (2013), pp.1-11.
https://search.emarefa.net/detail/BIM-1032883
American Medical Association (AMA)
Wang, Bin& Liu, Yu& Wang, Wei& Xu, Wei& Zhang, Maojun. Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition. The Scientific World Journal. 2013. Vol. 2013, no. 2013, pp.1-11.
https://search.emarefa.net/detail/BIM-1032883
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1032883