Feature Sequence Representation Via Slow Feature Analysis For Action Classification
Takumi Kobayashi
Abstract
The recent advances in extracting motion descriptors, such as BoW and CNN features, enable us to effectively convert a video into a sequence of frame-based feature
vectors. For improving the action classification performance, in this paper, we propose
an efficient method to represent the feature sequence by exploiting the temporal patterns
via slow feature analysis (SFA). The ordinary SFA suffers from small sample size (SSS)
problem found in action video clips and thus we propose PCA-SFA to cope with the SSS
problem by incorporating the information of PCA subspaces into SFA. The proposed
method leverages the PCA-SFA projection vector to describe the sequence of even fewer
frames by a fixed-dimensional video descriptor, capturing the essential temporal dynamics which is a slowly varying pattern embedded in the quickly varying input signals. The
computational cost to produce the video descriptor is negligible compared to the feature
extraction process such as BoW and CNN since the PCA-SFA is computed in a computationally efficient manner.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.125
https://dx.doi.org/10.5244/C.31.125
Citation
Takumi Kobayashi. Feature Sequence Representation Via Slow Feature Analysis For Action Classification. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 125.1-125.13. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_125,
title={Feature Sequence Representation Via Slow Feature Analysis For Action Classification},
author={Takumi Kobayashi},
year={2017},
month={September},
pages={125.1-125.13},
articleno={125},
numpages={13},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.125},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.125}
}