Presentation 2020-12-17
Simultaneous pose-region estimation for people tracking
Kazuhiko Watanabe, Toshikazu Wada,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bottom-up pose estimation often make an incorrect connection between body parts in a crowded situation like group photo. In this paper, we propose two DNN models: “Mask to Pose” that estimates people poses from their regions and “Pose to Mask” that estimates people regions from their poses. By combining these two models, we can estimate people regions and poses simultaneously.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Human Pose Estimation / Human Region Estimation / OpenPose
Paper # PRMU2020-41
Date of Issue 2020-12-10 (PRMU)

Conference Information
Committee PRMU
Conference Date 2020/12/17(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Transfer learning and few shot learning
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
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Simultaneous pose-region estimation for people tracking
Sub Title (in English)
Keyword(1) Human Pose Estimation
Keyword(2) Human Region Estimation
Keyword(3) OpenPose
1st Author's Name Kazuhiko Watanabe
1st Author's Affiliation Wakayama University(Wakayama Univ.)
2nd Author's Name Toshikazu Wada
2nd Author's Affiliation Wakayama University(Wakayama Univ.)
Date 2020-12-17
Paper # PRMU2020-41
Volume (vol) vol.120
Number (no) PRMU-300
Page pp.pp.18-23(PRMU),
#Pages 6
Date of Issue 2020-12-10 (PRMU)