Facial Expression Recognition Using Local Sliding Window Attention
There are problems associated with facial expression recognition (FER), such as facial occlusion and head pose variations. These two problems lead to incomplete facial information in images, making feature extraction extremely difficult. Most current methods use prior knowledge or fixed-size patches...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3424 |
| _version_ | 1827746490195378176 |
|---|---|
| author | Shuang Qiu Guangzhe Zhao Xiao Li Xueping Wang |
| author_facet | Shuang Qiu Guangzhe Zhao Xiao Li Xueping Wang |
| author_sort | Shuang Qiu |
| collection | DOAJ |
| description | There are problems associated with facial expression recognition (FER), such as facial occlusion and head pose variations. These two problems lead to incomplete facial information in images, making feature extraction extremely difficult. Most current methods use prior knowledge or fixed-size patches to perform local cropping, thereby enhancing the ability to acquire fine-grained features. However, the former requires extra data processing work and is prone to errors; the latter destroys the integrity of local features. In this paper, we propose a local Sliding Window Attention Network (SWA-Net) for FER. Specifically, we propose a sliding window strategy for feature-level cropping, which preserves the integrity of local features and does not require complex preprocessing. Moreover, the local feature enhancement module mines fine-grained features with intraclass semantics through a multiscale depth network. The adaptive local feature selection module is introduced to prompt the model to find more essential local features. Extensive experiments demonstrate that our SWA-Net model achieves a comparable performance to that of state-of-the-art methods with scores of 90.03% on RAF-DB, 89.22% on FERPlus, 63.97% on AffectNet. |
| first_indexed | 2024-03-11T05:26:06Z |
| format | Article |
| id | doaj.art-b49a7855cb654e8da91ae0b8c16e1b37 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:26:06Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b49a7855cb654e8da91ae0b8c16e1b372023-11-17T17:32:19ZengMDPI AGSensors1424-82202023-03-01237342410.3390/s23073424Facial Expression Recognition Using Local Sliding Window AttentionShuang Qiu0Guangzhe Zhao1Xiao Li2Xueping Wang3School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Electronics and Information Engineering, Zhongyuan University of Technology, Zhengzhou 450007, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaThere are problems associated with facial expression recognition (FER), such as facial occlusion and head pose variations. These two problems lead to incomplete facial information in images, making feature extraction extremely difficult. Most current methods use prior knowledge or fixed-size patches to perform local cropping, thereby enhancing the ability to acquire fine-grained features. However, the former requires extra data processing work and is prone to errors; the latter destroys the integrity of local features. In this paper, we propose a local Sliding Window Attention Network (SWA-Net) for FER. Specifically, we propose a sliding window strategy for feature-level cropping, which preserves the integrity of local features and does not require complex preprocessing. Moreover, the local feature enhancement module mines fine-grained features with intraclass semantics through a multiscale depth network. The adaptive local feature selection module is introduced to prompt the model to find more essential local features. Extensive experiments demonstrate that our SWA-Net model achieves a comparable performance to that of state-of-the-art methods with scores of 90.03% on RAF-DB, 89.22% on FERPlus, 63.97% on AffectNet.https://www.mdpi.com/1424-8220/23/7/3424facial expression recognitionsliding windowlocal feature enhancementadaptive feature selection |
| spellingShingle | Shuang Qiu Guangzhe Zhao Xiao Li Xueping Wang Facial Expression Recognition Using Local Sliding Window Attention Sensors facial expression recognition sliding window local feature enhancement adaptive feature selection |
| title | Facial Expression Recognition Using Local Sliding Window Attention |
| title_full | Facial Expression Recognition Using Local Sliding Window Attention |
| title_fullStr | Facial Expression Recognition Using Local Sliding Window Attention |
| title_full_unstemmed | Facial Expression Recognition Using Local Sliding Window Attention |
| title_short | Facial Expression Recognition Using Local Sliding Window Attention |
| title_sort | facial expression recognition using local sliding window attention |
| topic | facial expression recognition sliding window local feature enhancement adaptive feature selection |
| url | https://www.mdpi.com/1424-8220/23/7/3424 |
| work_keys_str_mv | AT shuangqiu facialexpressionrecognitionusinglocalslidingwindowattention AT guangzhezhao facialexpressionrecognitionusinglocalslidingwindowattention AT xiaoli facialexpressionrecognitionusinglocalslidingwindowattention AT xuepingwang facialexpressionrecognitionusinglocalslidingwindowattention |