E-FCNN for tiny facial expression recognition

Shao, Jie; Cheng, Qiyu

doi:10.1007/s10489-020-01855-5

Cited by 35 publications

(21 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TABLE 2. TABLE OF MODEL EXPERIMENT DATA Model Accuracy Parameters size VGG16 [5] 68.37% 138M DTGAN [10] 65.48% 5.8M Peak-Piloted [11] 65.64% 6.6M Frame2seq [7] 64.81% 2.6M Multi-C-Xception [12] 68.14% -E-FCNN [13] 66.17% -DAM-CNN [14] 65.31% -Ensemble-CNN [15] 73.73% -SIC-NET(Ours) 64.78% According to the experimental data in the table, the recognition accuracy of SIC-NET in the FER2013 dataset is 64.78%, and the number of model parameters is 1.2M. The recognition accuracy of SIC-NET is lower than that of other models, but the number of model parameters is the smallest and the real-time warning of the model is the best.…”

Section: Experiments Process and Results Analysismentioning

confidence: 99%

A Lightweight Two-Stream Model for Driver Emotion Recognition

Zhang

Yang

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In recent years, more and more attention has been paid to the traffic safety of drivers. Studies show that the motor vehicle speed will affect the incidence of traffic accidents and traffic accident casualty rate. In this paper, machine learning vision technology is used for real-time recognition of driver emotions, and a lightweight SIC-NET+RC-NET dual-stream recognition model is designed to cope with different scenarios of vehicle speed during driving. SIC-NET is a lightweight CNN network model, which greatly reduces the number of model parameters and computational power requirements, sacrifices part of accuracy, and greatly improves the real-time performance of model recognition. To improve the residual convolutional network model of inception blocks, RC-NET nested multiple micro-convolutional neural networks are used to identity mapping between different inception blocks to enhance the network training effect, expand network width and convolutional depth, and alleviate network degradation. This article stipulates that when the vehicle speed is greater than 60km/h, SIC-NET is used. When the vehicle speed is less than or equal to 60km/h, SIC-NET+RC-NRT is used. The FER2013 dataset was used for testing and validation in this paper. When SIC-NET is used, the model has better real-time performance and can provide a more timely warning when the vehicle speed is higher. When SIC-NET+RC-NET is used, the accuracy of the model in the FER2013 dataset is 69.65%, and the model can better cope with the scenario of a low vehicle speed. The experiment shows that the lightweight dual-flow model has good robustness and identification effect, which solves the problem of using the same model for different vehicle speeds and can effectively ensure the safety of the driver’s life and property.

show abstract

Section: Experiments Process and Results Analysismentioning

confidence: 99%

A Lightweight Two-Stream Model for Driver Emotion Recognition

Zhang

Yang

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The experimental results are shown in Figure 7. It turns out Methods Years Accuracy(%) Conv+Inception [30] 2016 66.40 SMFER [31] 2018 65.12 GoogleNet [32] 2018 65.20 VGG+SVM [33] 2019 66.31 SAP [34] 2019 71.08 E-FCNN [28] 2021 66.17 DeepEmotion [35] 2021 uses transfer learning technique to overcome the shortage of training samples. For FER2013, the second-highest recognition accuracy of the test set is SAP [34], which is a sample awareness-based expression recognition method, in which a Bayesian classifier is used to select the most appropriate classifier from a set of candidate classifiers for the current test sample, and then the classifier is used to perform expression recognition on the current sample.…”

Section: E Visualization Analysismentioning

confidence: 99%

RASN: Using Attention and Sharing Affinity Features to Address Sample Imbalance in Facial Expression Recognition

Yang

Kuang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The sample imbalance of expression datasets always leads to poor recognition results for minority classes. To solve this problem, we propose a facial expression recognition network, called Residual Attentive Sharing Network (RASN). There is a fact that different expressions have affinity features, which makes it possible for the minority classes to benefit from the majority classes in the expression feature extraction process, from which we propose a sharing affinity features module to compensate for the inadequate feature learning of minority classes by sharing affinity features. In addition, an affinity features attention module is added to highlight expression-related affinity features and suppress expression-unrelated ones for enhancing the role of sharing affinity features. Experiments on the CK+, RAF-DB, and FER2013 datasets validate the robustness of our method to sample imbalance. The validation accuracies of our method are 96.97% on CK+, 71.44% on FER2013, and 90.91% on RAF-DB, respectively, which exceed current state-of-the-art methods.

show abstract

“…In view of this, the relevant universities in China used deep learning and other technologies to conduct in-depth research on the facial expressions of the subjects and the classroom teaching effect. Literature [8] erefore, on the basis of existing research, this paper focuses on the inner relationship between face detection and classroom teaching effect evaluation and focuses on constructing a feasible classroom teaching effect evaluation model and applying it to teaching practice.…”

Section: Correlation Between Facial Expression Recognition Andmentioning

confidence: 99%

Improved Convolutional Neural Networks for Course Teaching Quality Assessment

Liu

2022

Advances in Multimedia

View full text Add to dashboard Cite

The cultivation of innovative talents is closely related to the quality of course teaching, and there is a correlation between facial expressions and the effectiveness of classroom teaching. In this paper, a separate long-term recursive convolutional network (SLRCN) microexpression recognition algorithm is proposed using deep learning technology for building a course teaching effectiveness evaluation model. Firstly, facial image sequences are extracted from microexpression data sets, and the transfer learning method is introduced to extract spatial features of facial expression frames through pretrained convolutional neural network model to reduce the risk of overfitting in network training. The extracted features of video sequences were input into long short-team memory (LSTM) to process temporal features. Experimental results show that SLRCN algorithm has the best performance in training set and test set. It has the best performance in ROC curve. This effectively distinguishes between seven different expressions in the database. The model proposed in this paper can obtain the changes of students’ facial expressions in class and evaluate students’ learning status, thus promoting the improvement of teaching quality. It provides a new method of course teaching quality evaluation.

show abstract

E-FCNN for tiny facial expression recognition

Cited by 35 publications

References 28 publications

A Lightweight Two-Stream Model for Driver Emotion Recognition

A Lightweight Two-Stream Model for Driver Emotion Recognition

RASN: Using Attention and Sharing Affinity Features to Address Sample Imbalance in Facial Expression Recognition

Improved Convolutional Neural Networks for Course Teaching Quality Assessment

Contact Info

Product

Resources

About