Two-Stream Flow-Guided Convolutional Attention Networks for Action Recognition
An Tran, Loong-Fah Cheong; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3110-3119
Abstract
This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos. The central idea is that optical flows, when properly compensated for the camera motion, can be used to guide attention to the human foreground. We thus develop cross-link layers from the temporal network (trained on flows) to the spatial network (trained on RGB frames). These cross-link layers guide the spatial-stream to pay more attention to the human foreground areas and be less affected by background clutter. We obtain promising performances with our approach on the UCF101 and HMDB51 datasets.
Related Material
[pdf]
[supp][arXiv][
bibtex]
@InProceedings{Tran_2017_ICCV,
author = {Tran, An and Cheong, Loong-Fah},
title = {Two-Stream Flow-Guided Convolutional Attention Networks for Action Recognition},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}