Presentation | 2021-03-04 [Short Paper] A CNN-Transformer-Based Network for Depression Recognition Liu Jiaqing, Huang Yue, Huang Xinren, Tateyama Tomoko, Iwamoto Yutaro, Chen Yanwei, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Depressive symptoms are a massive problem in this stressful modern society. Early screening of depressive symptoms helps to reduce the number and intensity of their depressive episodes. Automatic detection of depressive symptoms from audio cues has gained increasing interest in recent years. Transformer-based neural networks represent a successful self-attention mechanism that achieves state-of-the-art results in language understanding and sequence modeling. However, their application to visual data and, in particular, to the depressive severity detection task has not yet been deeply investigated. In this paper, we propose a transformer-based architecture for the depressive task. The temporal feature analysis using transformer computed after the feature extraction performed by DensNet. Our experimental results show that the proposed method can achieve CCC of 0.34 when using the validation set and 0.24 when using the test set, significantly outperforming the baseline method score CCC of 0.165. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | PRMU2020-83 |
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 | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Short Paper] A CNN-Transformer-Based Network for Depression Recognition |
Sub Title (in English) | |
Keyword(1) | |
Keyword(2) | |
Keyword(3) | |
Keyword(4) | |
Keyword(5) | |
1st Author's Name | Liu Jiaqing |
1st Author's Affiliation | Ritsumeikan University(Ritsumei) |
2nd Author's Name | Huang Yue |
2nd Author's Affiliation | Soochow University(Soochow) |
3rd Author's Name | Huang Xinren |
3rd Author's Affiliation | Soochow University(Soochow) |
4th Author's Name | Tateyama Tomoko |
4th Author's Affiliation | Shiga University(Shiga University) |
5th Author's Name | Iwamoto Yutaro |
5th Author's Affiliation | Ritsumeikan University(Ritsumei) |
6th Author's Name | Chen Yanwei |
6th Author's Affiliation | Ritsumeikan University(Ritsumei) |
Date | 2021-03-04 |
Paper # | PRMU2020-83 |
Volume (vol) | vol.120 |
Number (no) | PRMU-409 |
Page | pp.pp.83-85(PRMU), |
#Pages | 3 |
Date of Issue | 2021-02-25 (PRMU) |