Discriminant appearance weighting for action recognition

Tetsu Matsukawa, Takio Kurita

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

Extending popular histogram representations of local motion patterns, we present a novel weighted integration method based on an assumption that a motion importance should be changed by its appearance to obtain better recognition accuracies. The proposed integration method of motion and appearance patterns can weight information involving "what is moving" by discriminant way. The discriminant weights can be learned efficiently and naturally using two-dimensional fisher discriminant analysis (or, fisher weight maps) of co-occurrence matrices. Original fisher weight maps lose shift invariance of histogram features, while the proposed method preserves it. Experimental results on KTH human action dataset and UT-interaction dataset revealed the effectiveness of the proposed integration compared to naive integration methods of independent motion and appearance features and also other state-of-the-art methods.

本文言語英語
ホスト出版物のタイトル1st Asian Conference on Pattern Recognition, ACPR 2011
ページ7-11
ページ数5
DOI
出版ステータス出版済み - 2011
外部発表はい
イベント1st Asian Conference on Pattern Recognition, ACPR 2011 - Beijing, 中国
継続期間: 11 28 201111 28 2011

出版物シリーズ

名前1st Asian Conference on Pattern Recognition, ACPR 2011

その他

その他1st Asian Conference on Pattern Recognition, ACPR 2011
Country中国
CityBeijing
Period11/28/1111/28/11

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

フィンガープリント 「Discriminant appearance weighting for action recognition」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