Behavior Anomaly Detection Based on Multi-modal Feature Fusion and Its Application in English Teaching
In order to improve the teaching quality, this paper proposes a multi-modal feature fusion-based abnormal behavior detection method, aiming at the problems of false detection, missing detection and imbalance of positive and negative samples in the abnormal behavior detection of students in class. Th...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tamkang University Press
2025-02-01
|
| Series: | Journal of Applied Science and Engineering |
| Subjects: | |
| Online Access: | http://jase.tku.edu.tw/articles/jase-202509-28-09-0002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In order to improve the teaching quality, this paper proposes a multi-modal feature fusion-based abnormal behavior detection method, aiming at the problems of false detection, missing detection and imbalance of positive and negative samples in the abnormal behavior detection of students in class. The new method consists of encoder module, detection module and decoder module. The encoder module is used to extract the characteristic information of students behavior image and transfer it to the detection module. The behavior detection module obtains more image information through the feature fusion group to reduce the color distortion and artifacts of the behavior image, and transfers the obtained image information to the deep normalization
correction convolution block to reduce the covariate shift and make the model easier to train. The multi-path feature convolution block can obtain image information with richer texture details. Finally, the decoder module converts the low-dimensional feature mapping back to the high-dimensional original input space through deconvolution and up-sampling operations to obtain the behavior detection image. |
|---|---|
| ISSN: | 2708-9967 2708-9975 |