A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Representation Flow for Action Recognition
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the 'flow' of any representation channel within a convolutional neural network for action recognition. Its parameters for iterative flow optimization are learned in an end-to-end fashion together with the other model parameters, maximizing the action recognition performance. Furthermore, we newly
doi:10.1109/cvpr.2019.01018
dblp:conf/cvpr/PiergiovanniR19
fatcat:krlk6rwllncdzexb3tggmijvd4