Micro-expression recognition method based on progressive attention
Micro-expression is unconscious expression changes that reflect people's underlying emotions and inner states. When micro-expressions occur, their low intensity and the small facial range result in insufficient feature extraction and inaccurate localization of effective features during the r...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Science Press (China Science Publishing & Media Ltd.)
2024-11-01
|
| Series: | Shenzhen Daxue xuebao. Ligong ban |
| Subjects: | |
| Online Access: | https://journal.szu.edu.cn/en/#/digest?ArticleID=2671 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850041213547184128 |
|---|---|
| author | ZHAN Ziwei SUN Zhaocai LI Xiang WU Zhendong |
| author_facet | ZHAN Ziwei SUN Zhaocai LI Xiang WU Zhendong |
| author_sort | ZHAN Ziwei |
| collection | DOAJ |
| description | Micro-expression is unconscious expression changes that reflect people's underlying emotions and inner states. When micro-expressions occur, their low intensity and the small facial range result in insufficient feature extraction and inaccurate localization of effective features during the recognition process, which affects recognition accuracy. To address this issue, a progressive attention multi-scale convolutional network was constructed. The network integrates a multi-scale convolutional module and a progressive attention module. First, the multi-scale convolutional module is used to learn fine-grained features from different receptive fields, extracting rich details. Then, the progressive attention module is designed to accurately locate facial motion areas and robustly extract motion features from micro-expression images through information sharing and enhancement across multiple attention maps. The proposed network was tested on SMIC, CASMEII and SAMM datasets, achieving accuracy rates of 0.826, 0.880 and 0.787, and F1 scores of 0.817, 0.864 and 0.761, respectively. The proposed method can serve as an auxiliary tool for lie detection and early screening of mental health conditions. |
| format | Article |
| id | doaj-art-b877d04ba86d41cd830dc1aefff53c3a |
| institution | DOAJ |
| issn | 1000-2618 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Science Press (China Science Publishing & Media Ltd.) |
| record_format | Article |
| series | Shenzhen Daxue xuebao. Ligong ban |
| spelling | doaj-art-b877d04ba86d41cd830dc1aefff53c3a2025-08-20T02:55:49ZengScience Press (China Science Publishing & Media Ltd.)Shenzhen Daxue xuebao. Ligong ban1000-26182024-11-0141675676410.3724/SP.J.1249.2024.067561000-2618（2024）06-0756-09Micro-expression recognition method based on progressive attentionZHAN ZiweiSUN ZhaocaiLI XiangWU ZhendongMicro-expression is unconscious expression changes that reflect people's underlying emotions and inner states. When micro-expressions occur, their low intensity and the small facial range result in insufficient feature extraction and inaccurate localization of effective features during the recognition process, which affects recognition accuracy. To address this issue, a progressive attention multi-scale convolutional network was constructed. The network integrates a multi-scale convolutional module and a progressive attention module. First, the multi-scale convolutional module is used to learn fine-grained features from different receptive fields, extracting rich details. Then, the progressive attention module is designed to accurately locate facial motion areas and robustly extract motion features from micro-expression images through information sharing and enhancement across multiple attention maps. The proposed network was tested on SMIC, CASMEII and SAMM datasets, achieving accuracy rates of 0.826, 0.880 and 0.787, and F1 scores of 0.817, 0.864 and 0.761, respectively. The proposed method can serve as an auxiliary tool for lie detection and early screening of mental health conditions.https://journal.szu.edu.cn/en/#/digest?ArticleID=2671artificial intelligencemicro-expression recognitiondeep learningattention mechanismconvolutional neural networkmulti-scale convolutionlie detectionearly screening for mental health |
| spellingShingle | ZHAN Ziwei SUN Zhaocai LI Xiang WU Zhendong Micro-expression recognition method based on progressive attention Shenzhen Daxue xuebao. Ligong ban artificial intelligence micro-expression recognition deep learning attention mechanism convolutional neural network multi-scale convolution lie detection early screening for mental health |
| title | Micro-expression recognition method based on progressive attention |
| title_full | Micro-expression recognition method based on progressive attention |
| title_fullStr | Micro-expression recognition method based on progressive attention |
| title_full_unstemmed | Micro-expression recognition method based on progressive attention |
| title_short | Micro-expression recognition method based on progressive attention |
| title_sort | micro expression recognition method based on progressive attention |
| topic | artificial intelligence micro-expression recognition deep learning attention mechanism convolutional neural network multi-scale convolution lie detection early screening for mental health |
| url | https://journal.szu.edu.cn/en/#/digest?ArticleID=2671 |
| work_keys_str_mv | AT zhanziwei microexpressionrecognitionmethodbasedonprogressiveattention AT sunzhaocai microexpressionrecognitionmethodbasedonprogressiveattention AT lixiang microexpressionrecognitionmethodbasedonprogressiveattention AT wuzhendong microexpressionrecognitionmethodbasedonprogressiveattention |