Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Modeling Video Evolution For Action Recognition #1

Open
sgnoya opened this issue Nov 5, 2020 · 0 comments
Open

Modeling Video Evolution For Action Recognition #1

sgnoya opened this issue Nov 5, 2020 · 0 comments

Comments

@sgnoya
Copy link
Contributor

sgnoya commented Nov 5, 2020

1. 概要(基本アイデア)

  • 動画の表現方法として,Rank-SVMを基にした手法を提案.
  • 下記の条件を満たすベクトルuを見つけ特徴量として利用する.
  • uへ動画像の各フレームを射影した際に,u上での順序とフレームの時間順が一致するようにする.
    (時間が遅いフレームほど,内積値を大きくする.)

2. 新規性

Video/Temporal Evolutionを捉えるために,Rank-SVMを基にした動画記述子を提案.

3. 手法詳細

最適化はほぼRank-SVMと同じ.

4. 結果

5. 論文,コード等へのリンク

論文pdf

6. 感想,コメント

7. bibtex

@inproceedings{fernando2015modeling,
title={Modeling video evolution for action recognition},
author={Fernando, Basura and Gavves, Efstratios and Oramas, Jose M and Ghodrati, Amir and Tuytelaars, Tinne},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={5378--5387},
year={2015}
}

8. 関連論文

uを部分空間へ拡張
Generalized Rank Pooling for Activity Recognition, CVPR 2017

非線形部分空間へ
Non-Linear Temporal Subspace Representations for Activity Recognition, CVPR 2018

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant