首页|基于MOC改进的时空动作检测算法

基于MOC改进的时空动作检测算法

扫码查看
在时空动作检测领域,目前的一些研究试图利用无锚框的单阶段动作检测器来解决时空动作检测问题.论文提出了无锚框的单阶段检测器CFAMMOC.这个检测器建立在检测器MOC基础上,论文做了两点改进:1)为了有效提取出时空上下文信息,论文探索了一个通道融合与注意力模块,对提取到的单帧的特征进行聚合来增强特征的可辨识性;2)在原有的损失函数的基础上加入了IOU损失函数,提升了模型对动作实例边界框的回归能力.论文在两个基准数据集JHMDB和UCF101-24上进行实验,取得了和当前表现最好的算法不相上下的检测性能.
An Improved Spatio-tempora Action Detection Algorithm Based on MOC
In the field of spatio-temporal action detection,some current studies try to solve the spatio-temporal action detec-tion problem using one-stage action detector based on anchor-free.The paper proposes CFAMMOC,a single-stage detector with-out anchor,which is built on the basis of the detector MOC,and two improvements are made in this paper:1)to effectively extract spatio-temporal context information,a channel fusion and attention module is explored to enhance the feature discriminability by ag-gregating the features of the extracted single frames.2)An IOU loss function is added to the original loss function to enhance the re-gression capability of the model on the bounding box of action instances.It conducts experiments on two benchmark datasets,JHM-DB and UCF101-24,and the detection performance is achieved comparable to several state of the art methods.

spatio-temporal action detectionself attentionIOU loss functiondeep learning

谢伦伟、张翔、骆志刚

展开 >

国防科技大学计算机学院 长沙 410073

时空动作检测 自注意力 IOU损失函数 深度学习

2024

计算机与数字工程
中国船舶重工集团公司第七0九研究所

计算机与数字工程

CSTPCD
影响因子:0.355
ISSN:1672-9722
年,卷(期):2024.52(11)
  • 1