Incorporating temporal context in Bag-of-Words models

Bag-of-Words (BoW) is a highly popular model for recognition, due to its robustness and simplicity. Its modeling capabilities, however, are somewhat limited since it discards the spatial and temporal order of the codewords. In this paper we propose a new model: Contextual Sequence of Words (CSoW) wh...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) pp. 1562 - 1569
Main Authors Glaser, T., Zelnik-Manor, L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2011
Subjects
Context
Context modeling
Dictionaries
Histograms
Labeling
Robustness
Video sequences
Online AccessGet full text

Cover

More Information
Summary:Bag-of-Words (BoW) is a highly popular model for recognition, due to its robustness and simplicity. Its modeling capabilities, however, are somewhat limited since it discards the spatial and temporal order of the codewords. In this paper we propose a new model: Contextual Sequence of Words (CSoW) which incorporates temporal order into the BoW model for video representation. The temporal context is incorporated in three scales that capture different aspects of the variability between different performances of the same action. We show that using CSoW instead of BoW leads to a significant improvement in action recognition rates, on several different setups.
ISBN:1467300624
9781467300629
DOI:10.1109/ICCVW.2011.6130436