Presentation 2020-03-16
Egocentric Action Recognition on Noisy Videos
Lijin Yang, Yifei Huang, Yusuke Sugano, Yoichi Sato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Egocentric videos in real-life setting (like vlogs on YouTube) are often flooded with outlier frames and content-irrelevant shots, which dramatically reduce the action recognition accuracy and efficiency. In this work, we proposed a Sampler-Evaluator mechanism that could cooperate with any existing action recognition models and select informative frames from noisy input videos for them. Experiments shows that with our Sampler-Evaluator modules we can increase the action recognition performance of the backbone model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) egocentric action recognition / frame selection
Paper # PRMU2019-73
Date of Issue 2020-03-09 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2020/3/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Egocentric Action Recognition on Noisy Videos
Sub Title (in English)
Keyword(1) egocentric action recognition
Keyword(2) frame selection
1st Author's Name Lijin Yang
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Yifei Huang
2nd Author's Affiliation The University of Tokyo(UTokyo)
3rd Author's Name Yusuke Sugano
3rd Author's Affiliation The University of Tokyo(UTokyo)
4th Author's Name Yoichi Sato
4th Author's Affiliation The University of Tokyo(UTokyo)
Date 2020-03-16
Paper # PRMU2019-73
Volume (vol) vol.119
Number (no) PRMU-481
Page pp.pp.45-50(PRMU),
#Pages 6
Date of Issue 2020-03-09 (PRMU)