Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence(2021)
摘要
Accelerometric gait identification systems should ideally be robust to changes in device orientation from the enrollment phase to the deployment phase. However, traditional Convolutional Neural Networks (CNNs) used in these systems compensate poorly for such distributional shifts. In this paper, we target this problem by introducing an SO(3)-equivariant quaternion convolutional kernel inside the CNN. Our architecture (Quaternion CNN) significantly outperforms a traditional CNN in a multi-user gait classification setting. Additionally, the kernels learned by QCNN can be visualized as basis-independent trajectory fragments in Euclidean space, a novel mode of feature visualization and extraction.
更多查看译文
关键词
quaternion convolutional neural networks,convolutional neural networks,rotation-invariant
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要