Presentation | 2021-03-01 Action Detection Based on Supervised Contrastive Learning Keita Iida, Xueting Wang, Toshihiko Yamasaki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a method based on supervised contrastive learning in order to extract better feature for action detection. Action detection is still difficult and some actions are hard to detect. While actions related to actors' pose are easy to classify, those related to interactions with surroundings are not. Since the difficulty is partly caused by the variation of the actions, we propose a method for better feature extraction. By comparing with a standard supervised method, we show that the accuracy in some difficult labels has improved. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Action detection / Contrastive learning |
Paper # | IMQ2020-10,IE2020-50,MVE2020-42 |
Date of Issue | 2021-02-22 (IMQ, IE, MVE) |
Conference Information | |
Committee | MVE / IMQ / IE / CQ |
---|---|
Conference Date | 2021/3/1(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Masayuki Ihara(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Hideaki Kimata(NTT) / Hideyuki Shimonishi(NEC) |
Vice Chair | Kiyoshi Kiyokawa(NAIST) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
Secretary | Kiyoshi Kiyokawa(Oosaka Inst. of Tech.) / Mitsuru Maeda(NTT) / Kenya Uomori(Univ. of ToKyo) / Kazuya Kodama(Shizuoka Univ.) / Keita Takahashi(Sony Semiconductor Solutions) / Jun Okamoto(KDDI Research) / Takefumi Hiraguri(Nagoya Inst. of Tech.) |
Assistant | Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research) |
Paper Information | |
Registration To | Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Communication Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Action Detection Based on Supervised Contrastive Learning |
Sub Title (in English) | |
Keyword(1) | Action detection |
Keyword(2) | Contrastive learning |
1st Author's Name | Keita Iida |
1st Author's Affiliation | The University of Tokyo(The Univ. of Tokyo) |
2nd Author's Name | Xueting Wang |
2nd Author's Affiliation | The University of Tokyo(The Univ. of Tokyo) |
3rd Author's Name | Toshihiko Yamasaki |
3rd Author's Affiliation | The University of Tokyo(The Univ. of Tokyo) |
Date | 2021-03-01 |
Paper # | IMQ2020-10,IE2020-50,MVE2020-42 |
Volume (vol) | vol.120 |
Number (no) | IMQ-389,IE-390,MVE-391 |
Page | pp.pp.1-6(IMQ), pp.1-6(IE), pp.1-6(MVE), |
#Pages | 6 |
Date of Issue | 2021-02-22 (IMQ, IE, MVE) |