GMFL-Net:一种用于重复动作计数的全局多几何特征学习网络
GMFL-Net: A Global Multi-geometric Feature Learning Network for Repetitive Action Counting
AI总结:
本文提出GMFL-Net,通过MIA-Module融合多几何特征、GBFL-Module学习全局特征表示,并构建Countix-Fitness-pose数据集,在多个重复动作计数基准上取得最优性能。
摘要:
随着深度学习的持续发展,重复动作计数领域逐渐受到众多研究者的关注。利用人体姿态估计网络提取姿态关键点已被证明是一种有效的姿态级方法。然而,现有的姿态级方法存在以下不足:单一坐标不够稳定,难以应对因相机视角变化引起的动作形变,从而无法准确识别显著姿态,并且在从异常状态过渡到实际动作的过程中容易受到误检测的影响。为克服这些问题,我们提出了一种简单而高效的全局多几何特征学习网络(GMFL-Net)。具体来说,我们设计了一个MIA-Module,旨在通过融合多几何特征来改善信息表示,并学习输入多几何特征之间的语义相似性。然后,为了从全局视角改善特征表示,我们还设计了一个GBFL-Module,该模块增强逐点和逐通道元素之间的相互依赖关系,并将其与MIA-Module生成的丰富局部信息相结合,以合成一个全面且最具代表性的全局特征表示。此外,考虑到现有数据集的不足,我们收集了一个名为Countix-Fitness-pose的新数据集(https://github.com/Wantong66/Countix-Fitness),该数据集包含不同的周期长度和异常情况,以及一个持续时间更长的测试集,并在姿态级别上对其进行了细粒度标注。我们还新增了两个动作类别,即弓步和绳索下压。最后,在具有挑战性的RepCount-pose、UCFRep-pose和Countix-Fitness-pose基准上的大量实验表明,我们提出的GMFL-Net达到了最先进的性能。
英文摘要:
With the continuous development of deep learning, the field of repetitive action counting is gradually gaining notice from many researchers. Extraction of pose keypoints using human pose estimation networks is proven to be an effective pose-level method. However, existing pose-level methods suffer from the shortcomings that the single coordinate is not stable enough to handle action distortions due to changes in camera viewpoints, thus failing to accurately identify salient poses, and is vulnerable to misdetection during the transition from the exception to the actual action. To overcome these problems, we propose a simple but efficient Global Multi-geometric Feature Learning Network (GMFL-Net). Specifically, we design a MIA-Module that aims to improve information representation by fusing multi-geometric features, and learning the semantic similarity among the input multi-geometric features. Then, to improve the feature representation from a global perspective, we also design a GBFL-Module that enhances the inter-dependencies between point-wise and channel-wise elements and combines them with the rich local information generated by the MIA-Module to synthesise a comprehensive and most representative global feature representation. In addition, considering the insufficient existing dataset, we collect a new dataset called Countix-Fitness-pose (https://github.com/Wantong66/Countix-Fitness) which contains different cycle lengths and exceptions, a test set with longer duration, and annotate it with fine-grained annotations at the pose-level. We also add two new action classes, namely lunge and rope push-down. Finally, extensive experiments on the challenging RepCount-pose, UCFRep-pose, and Countix-Fitness-pose benchmarks show that our proposed GMFL-Net achieves state-of-the-art performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。