arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.00529cs.CVcs.LG
收藏

基于Capsule自编码器的无监督运动表示学习

Unsupervised Motion Representation Learning with Capsule Autoencoders

School of Computing(计算机学院);NUS Graduate School(新加坡国立大学研究生院);National University of Singapore(新加坡国立大学)

Ziwei Xu, Xudong Shen, Yongkang Wong, Mohan S Kankanhalli

摘要:

我们提出了运动胶囊自动编码器(MCAE),它解决了运动表示的无监督学习中的一个关键挑战:变换不变性。MCAE在两级层次结构中对运动进行建模。在较低的水平,时空运动信号被划分为短,本地和语义不可知的片段。在更高的级别中,片段被聚合以形成完整长度的语义感知片段。对于这两个级别,我们表示运动与一组学习的变换不变的模板和相应的几何变换,通过使用胶囊自动编码器的一种新颖的设计。这导致视点变化的鲁棒且高效的编码。MCAE是在一个新的Trajectory20运动数据集和各种真实世界的基于机器人的人类动作数据集上进行评估的。值得注意的是,它在Trajectory20上实现了比基线更好的结果,在无监督的基于动作识别任务上具有更少的参数和最先进的性能。

英文摘要:

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a spatio-temporal motion signal is divided into short, local, and semantic-agnostic snippets. In the higher level, the snippets are aggregated to form full-length semantic-aware segments. For both levels, we represent motion with a set of learned transformation invariant templates and the corresponding geometric transformations by using capsule autoencoders of a novel design. This leads to a robust and efficient encoding of viewpoint changes. MCAE is evaluated on a novel Trajectory20 motion dataset and various real-world skeleton-based human action datasets. Notably, it achieves better results than baselines on Trajectory20 with considerably fewer parameters and state-of-the-art performance on the unsupervised skeleton-based action recognition task.

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。

↑