Presentation | 2021-03-03 A Consideration on Estimation Accuracy Improvement of Unlearned Data in Video Viewer's Emotion Estimation Using Bio-signals Misato Matsumura, Mutsumi Suganuma, Wataru Kameyama, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We are conducting a research of video viewer’s emotion estimation from bio-signals using deep neural network in order to utilize it for video recommendation systems. In our previous results, the estimation accuracy of unlearned data is low, and it is considered that the number of training data is insufficient. So, the improvement of emotion estimation accuracy of unlearned data remains as an issue. Therefore, in this paper, we conduct an experiment using more videos and estimate emotions using more training data. As the result, the emotion estimation accuracy of unlearned data improves in 8 out of 9 subjects. We also consider how to determine the emotion labels, and find that the difficulty of the estimation seems to differ depending on the emotions. From these results, it is suggested that it is necessary to set up more appropriate emotion labels and to obtain a lot of training data in order to improve the emotion estimation accuracy of unlearned data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Bio-signals / Video Viewer / Emotion Estimation / Unlearned Data / Deep Neural Network |
Paper # | CQ2020-120 |
Date of Issue | 2021-02-22 (CQ) |
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) | A Consideration on Estimation Accuracy Improvement of Unlearned Data in Video Viewer's Emotion Estimation Using Bio-signals |
Sub Title (in English) | |
Keyword(1) | Bio-signals |
Keyword(2) | Video Viewer |
Keyword(3) | Emotion Estimation |
Keyword(4) | Unlearned Data |
Keyword(5) | Deep Neural Network |
1st Author's Name | Misato Matsumura |
1st Author's Affiliation | Waseda University(Waseda Univ.) |
2nd Author's Name | Mutsumi Suganuma |
2nd Author's Affiliation | Waseda University(Waseda Univ.) |
3rd Author's Name | Wataru Kameyama |
3rd Author's Affiliation | Waseda University(Waseda Univ.) |
Date | 2021-03-03 |
Paper # | CQ2020-120 |
Volume (vol) | vol.120 |
Number (no) | CQ-392 |
Page | pp.pp.67-72(CQ), |
#Pages | 6 |
Date of Issue | 2021-02-22 (CQ) |