Human Action Recognition by Random Features and Hand-Crafted Features: A Comparative Study
Abstract
One popular approach for human action recognition is to extract features from videos as representations, subsequently followed by a classification procedure of the representations. In this paper, we investigate and compare hand-crafted and random feature representation for human action recognition on YouTube dataset. The former is built on 3D HoG/HoF and SIFT descriptors while the latter bases on random projection. Three encoding methods: Bag of Feature(BoF), Sparse Coding(SC) and VLAD are adopted. Spatial temporal pyramid and a two-layer SVM classifier are employed for classification. Our experiments demonstrate that: 1) Sparse Coding is confirmed to outperform Bag of Feature; 2) Using a model of hybrid features incorporating frame-static can significantly improve the overall recognition accuracy; 3) The frame-static features works surprisingly better than motion features only; 4) Compared with the success of hand-crafted feature representation, the random feature representation does not perform well in this dataset.
Cite
Text
Shen et al. "Human Action Recognition by Random Features and Hand-Crafted Features: A Comparative Study." European Conference on Computer Vision Workshops, 2014. doi:10.1007/978-3-319-16181-5_2Markdown
[Shen et al. "Human Action Recognition by Random Features and Hand-Crafted Features: A Comparative Study." European Conference on Computer Vision Workshops, 2014.](https://mlanthology.org/eccvw/2014/shen2014eccvw-human/) doi:10.1007/978-3-319-16181-5_2BibTeX
@inproceedings{shen2014eccvw-human,
title = {{Human Action Recognition by Random Features and Hand-Crafted Features: A Comparative Study}},
author = {Shen, Haocheng and Zhang, Jianguo and Zhang, Hui},
booktitle = {European Conference on Computer Vision Workshops},
year = {2014},
pages = {14-28},
doi = {10.1007/978-3-319-16181-5_2},
url = {https://mlanthology.org/eccvw/2014/shen2014eccvw-human/}
}