.png){kind=icon}
返回
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108737.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Facial expression recognition focuses on extracting expression-related features on a face. In this paper, a novel method is proposed for facial expression modeling based on the following two aspects: seeking expression-related regions more accurately, and enhancing expression features more discriminating. To this end, we design a model containing three submodules: the Expression Feature Extractor ( EFE ), the Expression Mask Refiner ( EMR ), and the Expression Pattern-Map Generator ( EPMG ). The EFE module is the backbone that extracts expression features and generates a coarse attention mask which roughly indicates expression-related regions. The EMR module refines the mask to be more precise by modeling the relationship among expression-related regions, and generates the masked features. The EPMG module utilizes the masked features to further model the fusion and extraction process which obtains a compact and discriminating expression-salient embedding for recognition, and generates an expression pattern-map. We propose the concept of the expression pattern-map, which provides a unified visualization of expression features and improves the interpretability of facial expression recognition. Our model is evaluated on four public datasets (CK+, Oulu-CASIA, RAF-DB, AffectNet), and achieves the competitive performance compared with the state-of-the-art.
Keyword:
Facial expression recognition
Facial expression visualization
Expression pattern-map generator
Deep neural networks
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Occlusion Aware Facial Expression Recognition Using CNN With Attention Mechanism基于注意力机制的CNN遮挡感知面部表情识别
PREAI
分享收藏Deep multi-path convolutional neural network joint with salient region attention for facial expression recognition.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
Hard negative generation for identity-disentangled facial expression recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏
查看更多内容