MC-Net: Multiple max-pooling integration module and cross multi-scale deconvolution network

You, Hongfeng; Yu, Long; Tian, Shengwei; Ma, Xiang; Xing, Yan; Ning, Xin; Cai, Weiwei

doi:10.1016/j.knosys.2021.107456

Cited by 61 publications

(22 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, we used the NeuralNetTools package ( Beck, 2018 ) to obtain the relative importance (weight) of input variables (smile, eye contact, gesture, and tone) in the neural network ( Zhao et al, 2020 ; Chu et al, 2021 ; You et al, 2021 ; Zhang et al, 2021 ) through garson algorithm ( Ghanizadeh et al, 2020 ). As shown in Figure 3 , it can be found that the foreign language teacher’s eye contact and gesture have a greater influence on the decision of whether to improve students’ classroom learning efficiency (the weight of each variable is above 30%), followed by tone and smile (the weight of each variable is between 10 and 20%).…”

Section: Methods and Resultsmentioning

confidence: 99%

Foreign Language Teachers’ Emotion Recognition in College Oral English Classroom Teaching

Dai¹

2021

Front. Psychol.

View full text Add to dashboard Cite

One of the significant courses in Chinese universities is English. This course is usually taught by a foreign language instructor. There will, however, necessarily be some communication hurdles between “foreign language teachers” and “native students.” This research presents an emotion recognition method for foreign language teachers in order to eliminate communication barriers between teachers and students and improve student learning efficiency. We discovered four factors of emotion recognition through literature analysis: smile, eye contact, gesture, and tone. We believe that differences in foreign language teachers’ performance in these four areas will have an impact on students’ emotion recognition and, as a result, on their learning efficiency. The influence of the foreign language teacher’s eye contact and gestures is larger (the weight of a single variable accounted for 30% or more) in the decision whether can improve the students’ classroom learning efficiency, according to 43 of the questionnaire data analysis. The second is the tone and smile (the weight of a single variable accounted for between 10 and 20%). Our research contributes to the body of knowledge on emotion recognition in university foreign language teachers by presenting a practical method for recognizing emotion in foreign language teachers. We recommend that college foreign language teachers pay attention to eye and gesture communication with students in English classrooms based on the findings. By enriching the style of emotional expression in class, college language teachers, particularly foreign language teachers, can improve communication, and connection with students.

show abstract

Section: Methods and Resultsmentioning

confidence: 99%

Foreign Language Teachers’ Emotion Recognition in College Oral English Classroom Teaching

Dai¹

2021

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…The faster R-CNN algorithm proposed by Ren Shaoqing is famous for its efficient detection, and other scholars have proposed an improved algorithm based on the faster R-CNN algorithm. The implementation process of the faster R-CNN algorithm is shown in Figure 1 [ 9 , 10 ].…”

Section: Faster R-cnn Modelmentioning

confidence: 99%

Detection of Aerobics Action Based on Convolutional Neural Network

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To further improve the accuracy of aerobics action detection, a method of aerobics action detection based on improving multiscale characteristics is proposed. In this method, based on faster R-CNN and aiming at the problems existing in faster R-CNN, the feature pyramid network (FPN) is used to extract aerobics action image features. So, the low-level semantic information in the images can be extracted, and it can be converted into high-resolution deep-level semantic information. Finally, the target detector is constructed by the above-extracted anchor points so as to realize the detection of aerobics action. The results show that the loss function of the neural network is reduced to 0.2 by using the proposed method, and the accuracy of the proposed method can reach 96.5% compared with other methods, which proves the feasibility of this study.

show abstract

“…In the classification, the cross-entropy function is chosen. The basic structure of the network is shown below [ 26 ]:…”

Section: Cultural Relic Recognition Based On Self-attention Concentrationmentioning

confidence: 99%

Museum Relic Image Detection and Recognition Based on Deep Learning

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To improve the accuracy of museum cultural relic image recognition, the DenseNet and ResNet are selected as the backbone neural networks for detection and recognition. In view of the small target problem in cultural relics, the feature pyramid is introduced in this paper to improve the DenseNet method. The accuracy of target detection is improved through multiscale feature extraction and fusion. At the same time, aiming the problem of weak robustness and feature extraction of cultural relic images, the attention mechanism is proposed to improve ResNet. Therefore, this network can pay attention to the key of feature areas in the image. Finally, the aforementioned methods are verified by experiments. The results show that compared with the YOLOv3 and other algorithms, the accuracy of the improved ResNet proposed in this experiment is above 90%. Furthermore, the number of missed and erroneous detection is the lowest, which are 171 and 134, respectively. The identified mAP indicator accuracy can reach 86%, which also exceeds SVD-Net and DenseNet. It can be seen that the constructed method can effectively detect and recognize the museum cultural relic images.

show abstract

MC-Net: Multiple max-pooling integration module and cross multi-scale deconvolution network

Cited by 61 publications

References 43 publications

Foreign Language Teachers’ Emotion Recognition in College Oral English Classroom Teaching

Foreign Language Teachers’ Emotion Recognition in College Oral English Classroom Teaching

Detection of Aerobics Action Based on Convolutional Neural Network

Museum Relic Image Detection and Recognition Based on Deep Learning

Contact Info

Product

Resources

About