The past decade has witnessed significant advances in time series modeling
with deep learning. While achieving state-of-the-art results, the
best-performing architectures vary highly across applications and domains. On
the other hand, for natural language processing, Generative Pre-trained
Transformer (GPT) has demonstrated impressive performance via training one
general-purpose model across various textual datasets. It is intriguing to
explore whether GPT-type architectures can be effective for time series,
capturing the intrinsic dynamic attributes and leading to significant accuracy
improvements. In this paper, we propose a novel framework, TEMPO, that can
effectively learn time series representations. We focus on utilizing two
essential inductive biases of the time series task for pre-trained models: (i)
decomposition of the complex interaction between trend, seasonal and residual
components; and (ii) introducing the selection-based prompts to facilitate
distribution adaptation in non-stationary time series. TEMPO expands the
capability for dynamically modeling real-world temporal phenomena from data
within diverse domains. Our experiments demonstrate the superior performance of
TEMPO, with 20\%-60\% improvement over state-of-the-art methods on a number of
time series benchmark datasets. This performance gain is observed not only in
standard supervised learning settings but also in scenarios involving
previously unseen datasets. This compelling finding highlights \modelname's
potential to constitute a foundational model building framework.

TEMPO 是一个基于时间序列的新框架，通过利用时序任务的两个基本归纳偏好来有效学习时间序列表示，展现出超过 20% 至 60% 的改善性能，并在标准监督学习和之前未见数据集的情景中观察到。

TEMPO：面向时间序列预测的基于提示的生成预训练变换器

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series  Forecasting

Existing volumetric methods for predicting 3D human pose estimation are
accurate, but computationally expensive and optimized for single time-step
prediction. We present TEMPO, an efficient multi-view pose estimation model
that learns a robust spatiotemporal representation, improving pose accuracy
while also tracking and forecasting human pose. We significantly reduce
computation compared to the state-of-the-art by recurrently computing
per-person 2D pose features, fusing both spatial and temporal information into
a single representation. In doing so, our model is able to use spatiotemporal
context to predict more accurate human poses without sacrificing efficiency. We
further use this representation to track human poses over time as well as
predict future poses. Finally, we demonstrate that our model is able to
generalize across datasets without scene-specific fine-tuning. TEMPO achieves
10$\%$ better MPJPE with a 33$\times$ improvement in FPS compared to TesseTrack
on the challenging CMU Panoptic Studio dataset.

TEMPO 是一种高效的多视角姿势估计模型，通过学习稳健的时空表示，提高了姿势准确性，同时还能跟踪和预测人体姿势。该模型通过循环计算个人的二维姿势特征，将空间和时间信息融合成一种表示，并利用时空上下文预测更准确的人体姿势，同时保持高效性。该模型能够跨数据集泛化而无需场景特定微调，达到了相比 TesseTrack 在具有挑战性的 CMU Panoptic Studio 数据集上 MPJPE 提升 10%，帧率提升 33 倍的效果。