郑州大学学报（理学版）2025，Vol.57Issue(3)：65-71,7.DOI:10.13705/j.issn.1671-6841.2023171
结合ResNet和CBAM的静态图像行为识别方法
Still Image Action Recognition Method Combining ResNet and CBAM
摘要
Abstract
To address the problem of poor recognition performance caused by the lack of large-scale data-sets and the inability to utilize spatiotemporal features,a model that combined residual neural network(ResNet)and convolutional block attention module(CBAM)was proposed for still image action recogni-tion.Specific data augmentation techniques were employed to extend the dataset.Transfer learning was applied to initialize the model,followed by fine-tuning to enhance feature representation of still image ac-tion recognition.The CBAM was embedded into the first convolutional layer of ResNet to adjust the mod-el's attention.The Grad-CAM method was utilized to extract and visualize the regions of interest in image which provided an explanation for the precision improvement.On the PPMI dataset,the proposed model achieved the average precision for instrument-playing,instrument-holding,and overall categories of 88.30％,81.94％and 77.93％,respectively,which verified the effectiveness of the method.关键词
残差网络/行为识别/卷积注意力模块/静态图像/迁移学习Key words
residual network/action recognition/convolutional block attention module/still image/transfer learning分类
计算机与自动化引用本文复制引用
高晗,万方杰,马明旭..结合ResNet和CBAM的静态图像行为识别方法[J].郑州大学学报（理学版）,2025,57(3):65-71,7.基金项目
河南省重大专项(221100210100) （221100210100）
