Presentation 2021-03-05
Cross-view Non-local Neural Networks for Joint Representation Learning between First and Third Person Videos
Zhehao Zhu, Yusuke Sugano, Yoichi Sato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper introduces a cross-view non-local neural network to learn joint representations for understandinghuman activities from videos captured by wearable and fixed cameras. The key element is a non-local model to extract andenhance the global visual feature similarity across the views while reducing dissimilarity. The proposed method achieves astate-of-the-art performance on a cross-view action recognition benchmark dataset.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Non-local neural networksJoint representation learning
Paper # PRMU2020-99
Date of Issue 2021-02-25 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2021/3/4(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Computer Vision and Pattern Recognition for specific environment
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.)
Secretary Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.)
Assistant Takashi Shibata(NTT) / Masashi Nishiyama(Tottori 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) Cross-view Non-local Neural Networks for Joint Representation Learning between First and Third Person Videos
Sub Title (in English)
Keyword(1) Non-local neural networksJoint representation learning
1st Author's Name Zhehao Zhu
1st Author's Affiliation University of Tokyo(UTokyo)
2nd Author's Name Yusuke Sugano
2nd Author's Affiliation University of Tokyo(UTokyo)
3rd Author's Name Yoichi Sato
3rd Author's Affiliation University of Tokyo(UTokyo)
Date 2021-03-05
Paper # PRMU2020-99
Volume (vol) vol.120
Number (no) PRMU-409
Page pp.pp.170-175(PRMU),
#Pages 6
Date of Issue 2021-02-25 (PRMU)