Cross-view action recognition is a challenging research field for human motion analysis. Appearance-based features are not credible if the viewpoint changes. In this paper, a new framework is proposed for cross-view action recognition by topic based knowledge transfer. First, Spatio-temporal descriptors are extracted from the action videos and each video is modeled by a bag of visual words (BoVW) based on the codebook constructed by the k-means cluster algorithm. Second, Latent Dirichlet Allocation (LDA) is employed to assign topics for the BoVW representation. The topic distribution of visual words (ToVW) is normalized and taken to be the feature vector. Third, in order to bridge different views, we transform ToVW into bilingual ToVW by constructing bilingual dictionaries, which guarantee that the same action has the same representation from different views. We demonstrate the effectiveness of the proposed algorithm on the IXMAS multi-view dataset.
Changhong CHEN
Nanjing University of Posts and Telecommunications
Shunqing YANG
Nanjing University of Posts and Telecommunications
Zongliang GAN
Nanjing University of Posts and Telecommunications
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Changhong CHEN, Shunqing YANG, Zongliang GAN, "Topic-Based Knowledge Transfer Algorithm for Cross-View Action Recognition" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 3, pp. 614-617, March 2014, doi: 10.1587/transinf.E97.D.614.
Abstract: Cross-view action recognition is a challenging research field for human motion analysis. Appearance-based features are not credible if the viewpoint changes. In this paper, a new framework is proposed for cross-view action recognition by topic based knowledge transfer. First, Spatio-temporal descriptors are extracted from the action videos and each video is modeled by a bag of visual words (BoVW) based on the codebook constructed by the k-means cluster algorithm. Second, Latent Dirichlet Allocation (LDA) is employed to assign topics for the BoVW representation. The topic distribution of visual words (ToVW) is normalized and taken to be the feature vector. Third, in order to bridge different views, we transform ToVW into bilingual ToVW by constructing bilingual dictionaries, which guarantee that the same action has the same representation from different views. We demonstrate the effectiveness of the proposed algorithm on the IXMAS multi-view dataset.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.614/_p
Copy
@ARTICLE{e97-d_3_614,
author={Changhong CHEN, Shunqing YANG, Zongliang GAN, },
journal={IEICE TRANSACTIONS on Information},
title={Topic-Based Knowledge Transfer Algorithm for Cross-View Action Recognition},
year={2014},
volume={E97-D},
number={3},
pages={614-617},
abstract={Cross-view action recognition is a challenging research field for human motion analysis. Appearance-based features are not credible if the viewpoint changes. In this paper, a new framework is proposed for cross-view action recognition by topic based knowledge transfer. First, Spatio-temporal descriptors are extracted from the action videos and each video is modeled by a bag of visual words (BoVW) based on the codebook constructed by the k-means cluster algorithm. Second, Latent Dirichlet Allocation (LDA) is employed to assign topics for the BoVW representation. The topic distribution of visual words (ToVW) is normalized and taken to be the feature vector. Third, in order to bridge different views, we transform ToVW into bilingual ToVW by constructing bilingual dictionaries, which guarantee that the same action has the same representation from different views. We demonstrate the effectiveness of the proposed algorithm on the IXMAS multi-view dataset.},
keywords={},
doi={10.1587/transinf.E97.D.614},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Topic-Based Knowledge Transfer Algorithm for Cross-View Action Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 614
EP - 617
AU - Changhong CHEN
AU - Shunqing YANG
AU - Zongliang GAN
PY - 2014
DO - 10.1587/transinf.E97.D.614
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2014
AB - Cross-view action recognition is a challenging research field for human motion analysis. Appearance-based features are not credible if the viewpoint changes. In this paper, a new framework is proposed for cross-view action recognition by topic based knowledge transfer. First, Spatio-temporal descriptors are extracted from the action videos and each video is modeled by a bag of visual words (BoVW) based on the codebook constructed by the k-means cluster algorithm. Second, Latent Dirichlet Allocation (LDA) is employed to assign topics for the BoVW representation. The topic distribution of visual words (ToVW) is normalized and taken to be the feature vector. Third, in order to bridge different views, we transform ToVW into bilingual ToVW by constructing bilingual dictionaries, which guarantee that the same action has the same representation from different views. We demonstrate the effectiveness of the proposed algorithm on the IXMAS multi-view dataset.
ER -