Time series analysis plays a critical role in numerous applications, supporting tasks such as forecasting, classification, anomaly detection, and imputation. In this work, we present the time series pattern machine (TSPM), a model designed to excel in a broad range of time series tasks through powerful representation and pattern extraction capabilities. Traditional time series models often struggle to capture universal patterns, limiting their effectiveness across diverse tasks. To address this, we define multiple scales in the time domain and various resolutions in the frequency domain, employing various mixing strategies to extract intricate, task-adaptive time series patterns. MRTI transforms multi-scale time series into multi-resolution time images, capturing patterns across both temporal and frequency domains. TID leverages dual-axis attention to extract seasonal and trend patterns, while MCM hierarchically aggregates these patterns across scales. Our work marks a promising step toward the next generation of TSPMs, paving the way for further advancements in time series analysis. Time series analysis is crucial for identifying and predicting temporal patterns across various domains, including weather forecasting (Bi et al., 2023), medical symptom classification (Kiyasseh et al., 2021), anomaly detection in spacecraft monitoring (Xu, 2021), and imputing missing data in wearable sensors (Wu et al., 2020). These diverse applications highlight the versatility and importance of time series analysis in addressing real-world challenges. A key advancement in this field is the development of time series pattern machines (TSPMs), which aim to create a unified model architecture capable of handling a broad range of time series tasks across domains (Zhou et al., 2023; Wu et al., 2023). At the core of TSPMs is their ability to recognize and generalize time series patterns inherent in time series data, enabling the model to uncover meaningful temporal structures and adapt to varying time series task scenarios.

Traffic sign identification using camera images from vehicles plays a critical role in autonomous driving and path planning. However, the front camera images can be distorted due to blurriness, lighting variations and vandalism which can lead to degradation of detection performances. As a solution, machine learning models must be trained with data from multiple domains, and collecting and labeling more data in each new domain is time consuming and expensive. In this work, we present an end-to-end framework to augment traffic sign training data using optimal reinforcement learning policies and a variety of Generative Adversarial Network (GAN) models, that can then be used to train traffic sign detector modules. Our automated augmenter enables learning from transformed nightime, poor lighting, and varying degrees of occlusions using the LISA Traffic Sign and BDD-Nexar dataset. The proposed method enables mapping training data from one domain to another, thereby improving traffic sign detection precision/recall from 0.70/0.66 to 0.83/0.71 for nighttime images.