An Attention-Based Activity Recognition for Egocentric Video
Abstract
In this paper, we propose a human activity recognition method from first-person videos, which provides a supplementary method to improve the recognition accuracy. Conventional methods detect objects and derive a user's behavior based on their taxonomy. One of the recent works has achieved accuracy improvement by determining key objects based on hand manipulation. However, such manipulation-based approach has a restriction on applicable scenes and object types because the user's hands don't always present significant information. In contrast, our proposed attention-based approach provides a solution to detect visually salient objects as key objects in a non-contact manner. Experimental results show that the proposed method classifies first-person actions more accurately than the previous method by 6.4 percentage points and its average accuracy reaches 43.3%.
Cite
Text
Matsuo et al. "An Attention-Based Activity Recognition for Egocentric Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014. doi:10.1109/CVPRW.2014.87Markdown
[Matsuo et al. "An Attention-Based Activity Recognition for Egocentric Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2014.](https://mlanthology.org/cvprw/2014/matsuo2014cvprw-attentionbased/) doi:10.1109/CVPRW.2014.87BibTeX
@inproceedings{matsuo2014cvprw-attentionbased,
title = {{An Attention-Based Activity Recognition for Egocentric Video}},
author = {Matsuo, Kenji and Yamada, Kentaro and Ueno, Satoshi and Naito, Sei},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2014},
pages = {565-570},
doi = {10.1109/CVPRW.2014.87},
url = {https://mlanthology.org/cvprw/2014/matsuo2014cvprw-attentionbased/}
}