Bi-directional attention flow for video alignment

Reham Abobeah, Marwan Torki, Amin Shoukry, Jiro Katto

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルVISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
編集者Andreas Kerren, Christophe Hurter, Jose Braz
出版社SciTePress
ページ583-589
ページ数7
ISBN(電子版)9789897583544
出版ステータスPublished - 2019
イベント14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 - Prague, Czech Republic
継続期間: 2019 2月 252019 2月 27

出版物シリーズ

名前VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
5

Conference

Conference14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019
国/地域Czech Republic
CityPrague
Period19/2/2519/2/27

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • コンピュータ グラフィックスおよびコンピュータ支援設計

フィンガープリント

「Bi-directional attention flow for video alignment」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル