arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.09413cs.CVcs.MM
收藏

基于自注意的锚点算法在基于动作识别中的应用

Self-attention based anchor proposal for skeleton-based action recognition

Zhejiang University(浙江大学);Bournemouth University(伯恩茅斯大学)

Ruijie Hou, Zhao Wang

摘要:

骨架序列由于其轻量级和紧凑的特点被广泛应用于动作识别任务。由于图卷积网络具有良好的非欧数据建模能力,近年来的图卷积网络(GCN)方法在基于卷积的动作识别中取得了巨大的成功。GCN能够利用短距离的关节依赖关系,而缺乏直接建模的远距离关节关系,是至关重要的区分各种行动。因此,许多GCN方法试图采用分层机制来聚合更广泛的邻域信息。我们提出了一种新的基于自注意力的锚点建议(SAP)模块,全面建模的内部关系的人体运动特征学习。所提出的SAP模块旨在通过编码高阶角度信息而不是现有分层GCN方法中使用的固定成对骨连接,使用三元组表示来探索人体内的固有关系。在SAP模块中设计了一种基于自注意的锚点选择方法,用于提取编码角度信息的根点。通过将所提出的SAP模块与流行的时空图神经网络(例如MSG3D)耦合,它在具有挑战性的基准数据集上实现了新的最先进的精度。进一步的消融研究表明,我们提出的SAP模块的有效性,这是能够显着提高性能的许多流行的基于动作识别方法。

英文摘要:

Skeleton sequences are widely used for action recognition task due to its lightweight and compact characteristics. Recent graph convolutional network (GCN) approaches have achieved great success for skeleton-based action recognition since its grateful modeling ability of non-Euclidean data. GCN is able to utilize the short-range joint dependencies while lack to directly model the distant joints relations that are vital to distinguishing various actions. Thus, many GCN approaches try to employ hierarchical mechanism to aggregate wider-range neighborhood information. We propose a novel self-attention based skeleton-anchor proposal (SAP) module to comprehensively model the internal relations of a human body for motion feature learning. The proposed SAP module aims to explore inherent relationship within human body using a triplet representation via encoding high order angle information rather than the fixed pair-wise bone connection used in the existing hierarchical GCN approaches. A Self-attention based anchor selection method is designed in the proposed SAP module for extracting the root point of encoding angular information. By coupling proposed SAP module with popular spatial-temporal graph neural networks, e.g. MSG3D, it achieves new state-of-the-art accuracy on challenging benchmark datasets. Further ablation study have shown the effectiveness of our proposed SAP module, which is able to obviously improve the performance of many popular skeleton-based action recognition methods.

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。

↑