Publication Type
Journal Article
Version
publishedVersion
Publication Date
1-2016
Abstract
Bag-of-Words (BOW) histogram of local space-time features is very popular for action representation due to its high compactness and robustness. However, its discriminant ability is limited since it only depends on the occurrence statistics of local features. Alternative models such as Vector of Locally Aggregated Descriptors (VLAD) and Fisher Vectors (FV) include more information by aggregating high-dimensional residual vectors, but they suffer from the problem of high dimensionality for final representation. To solve this problem, we novelly propose to compress residual vectors into low-dimensional residual histograms by the simple but efficient BoW quantization. To compensate the information loss of this quantization, we iteratively collect higher-order residual vectors to produce high-order residual histograms. Concatenating these histograms yields a hierarchical BoW (HBoW) model which is not only compact but also informative. In experiments, the performances of HBoW are evaluated on four benchmark datasets: HMDB51, Olympic Sports, UCF Youtube and Hollywood2. Experiment results show that HBoW yields much more compact action representation than VLAD and FV, without sacrificing recognition accuracy. Comparisons with state-of-the-art works confirm its superiority further. (C) 2015 Elsevier B.V. All rights reserved.
Keywords
Action representation, Bag-of-Words, Vector of Locally Aggregated Descriptors, Fisher Vectors
Discipline
Computer and Systems Architecture | Computer Engineering
Research Areas
Data Science and Engineering
Publication
Neurocomputing
Volume
174
First Page
722
Last Page
732
ISSN
0925-2312
Identifier
10.1016/j.neucom.2015.09.074
Publisher
Elsevier
Citation
SUN, Qianru; Qianru; LIU, Hong; LIU, Hong; MA, Liqian; and ZHANG, Tianwei.
A novel hierarchical Bag-of-Words model for compact action representation. (2016). Neurocomputing. 174, 722-732.
Available at: https://ink.library.smu.edu.sg/sis_research/4452
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1016/j.neucom.2015.09.074