arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.11036cs.CV
收藏

DWnet:用于3D动作识别的深度网络

DWnet: Deep-Wide Network for 3D Action Recognition

Beijing University of Posts and Telecommunication(北京邮电大学)

Yonghao Dang, Fuxing Yang, Jianqin Yin

摘要:

在本文中,我们提出了一种深度宽网络(DWnet),它结合了深层结构与广泛的学习系统(BLS)来识别动作。与深层结构相比,该模型节省了大量的测试时间,几乎实现了实时测试。此外,DWnet可以捕获比广义学习系统更好的特征。在方法论上,我们使用修剪层次共现网络(PruHCN)来学习局部和全局时空特征。为了获得足够的全局信息,BLS被用来扩展由PruHCN提取的特征。在两个常见的骨骼数据集上的实验表明,该模型在测试时间上的优势和新模型识别动作的有效性。

英文摘要:

We propose in this paper a deep-wide network (DWnet) which combines the deep structure with the broad learning system (BLS) to recognize actions. Compared with the deep structure, the novel model saves lots of testing time and almost achieves real-time testing. Furthermore, the DWnet can capture better features than broad learning system can. In terms of methodology, we use pruned hierarchical co-occurrence network (PruHCN) to learn local and global spatial-temporal features. To obtain sufficient global information, BLS is used to expand features extracted by PruHCN. Experiments on two common skeletal datasets demonstrate the advantage of the proposed model on testing time and the effectiveness of the novel model to recognize the action.

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。

↑