Bi-Directional Attention Flow for Video Alignment

Reham Abobeah, Marwan Torki, Amin Shoukry, Jiro Katto

Abstract

In this paper, a novel technique is introduced to address the video alignment task which is one of the hot topics in computer vision. Specifically, we aim at finding the best possible correspondences between two overlapping videos without the restrictions imposed by previous techniques. The novelty of this work is that the video alignment problem is solved by drawing an analogy between it and the machine comprehension (MC) task in natural language processing (NLP). Simply, MC seeks to give the best answer to a question about a given paragraph. In our work, one of the two videos is considered as a query, while the other as a context. First, a pre-trained CNN is used to obtain high-level features from the frames of both the query and context videos. Then, the bidirectional attention flow mechanism; that has achieved considerable success in MC; is used to compute the query-context interactions in order to find the best mapping between the two input videos. The proposed model has been trained using 10k of collected video pairs from ”YouTube”. The initial experimental results show that it is a promising solution for the video alignment task when compared to the state of the art techniques.

Download


Paper Citation


in Harvard Style

Abobeah R., Torki M., Shoukry A. and Katto J. (2019). Bi-Directional Attention Flow for Video Alignment.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-354-4, pages 583-589. DOI: 10.5220/0007524505830589


in Bibtex Style

@conference{visapp19,
author={Reham Abobeah and Marwan Torki and Amin Shoukry and Jiro Katto},
title={Bi-Directional Attention Flow for Video Alignment},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2019},
pages={583-589},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007524505830589},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Bi-Directional Attention Flow for Video Alignment
SN - 978-989-758-354-4
AU - Abobeah R.
AU - Torki M.
AU - Shoukry A.
AU - Katto J.
PY - 2019
SP - 583
EP - 589
DO - 10.5220/0007524505830589