Research on Exam Behavior Recognition Based on Efficientnet Improvement

This article addresses issues such as poor real-time recognition of student exam behavior and difficulty in detecting small targets.Firstly, the attention CBAM module is introduced to perform attention operations in both spatial and channel dimensions, making the model more focused on the target object.Secondly, the feature fusion module is improved in Efficientnet to enable the model to obtain more small target features and further enhance its ability to detect small targets; Based on these optimization methods, a new object detection model EfficientZet-L-S was developed, and automatic recognition experiments were conducted using simulated exam scene video data.The average accuracy of identifying inappropriate behavior in the examination room increased from 75.6% to 81.3%.