Time Series Classification (TSC) is an important and challenging task for many visual computing applications. Despite the extensive range of methods developed for TSC, relatively few utilized Deep Neural Networks (DNNs). In this paper, we propose two novel attention blocks (Global Temporal Attention and Temporal Pseudo-Gaussian augmented Self-Attention) that can enhance deep learning-based TSC approaches, even when such approaches are designed and optimized for a specific dataset or task. We validate this claim by evaluating multiple state-of-the-art deep learning-based TSC models on the University of East Anglia (UEA) benchmark, a standardized collection of 30 Multivariate Time Series Classification (MTSC) datasets. We show that adding the proposed attention blocks improves base models' average accuracy by up to 3.6%. Additionally, the proposed TPS block uses a new injection module to include the relative positional information in transformers. As a standalone unit with less computational complexity, it enables TPS to perform better than most of the state-of-the-art DNN-based TSC methods. The source codes for our experimental setups and proposed attention blocks are made publicly available.

翻译：时间序列分类（TSC）是许多视觉计算应用中一项重要且具有挑战性的任务。尽管已开发出大量TSC方法，但应用深度神经网络（DNN）的方法相对较少。本文提出两种新颖的注意力模块（全局时间注意力与时序伪高斯增强自注意力），即使现有基于深度学习的TSC方法已针对特定数据集或任务进行设计和优化，这两种模块仍能提升其性能。我们通过在东英吉利大学（UEA）基准（包含30个多变量时间序列分类（MTSC）数据集的标准化集合）上评估多种最先进的基于深度学习的TSC模型，验证了这一论断。结果表明，加入所提出的注意力模块可使基模型的平均准确率提升高达3.6%。此外，所提出的TPS模块采用一种新的注入机制将相对位置信息引入Transformer中。作为计算复杂度更低的独立单元，TPS的性能优于大多数最先进的基于DNN的TSC方法。我们已公开实验设置及所提注意力模块的源代码。