Learning Video Representations From Correspondence Proposals

Xingyu Liu, Joon-Young Lee, Hailin Jin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4273-4281

Abstract


Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a novel neural network that learns video representations by aggregating information from potential correspondences. This network, named CPNet, can learn evolving 2D fields with temporal consistency. In particular, it can effectively learn representations for videos by mixing appearance and long-range motion with an RGB-only input. We provide extensive ablation experiments to validate our model. CPNet shows stronger performance than existing methods on Kinetics and achieves the state-of-the-art performance on Something-Something and Jester. We provide analysis towards the behavior of our model and show its robustness to errors in proposals.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Liu_2019_CVPR,
author = {Liu, Xingyu and Lee, Joon-Young and Jin, Hailin},
title = {Learning Video Representations From Correspondence Proposals},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}