paper-with-me

Papers

Diagnostic Spatio-temporal Transformer with Faithful Encoding

2023-05-26 · Jokin Labaien, Tsuyoshi Idé, Pin-Yu Chen, Ekhi Zugasti, Xabier De Carlos

This paper addresses the task of anomaly diagnosis when the underlying data generation process has a complex spatio-temporal (ST) dependency. The key technical challenge is to extract actionable insights from the dependency tensor characterizing high-order interactions among temporal and spatial indices. We formalize the problem as supervised dependency discovery, where the ST dependency is learned as a side product of multivariate time-series classification. We show that temporal positional encoding used in existing ST transformer works has a serious limitation in capturing higher frequencies (short time scales). We propose a new positional encoding with a theoretical guarantee, based on discrete Fourier transform. We also propose a new ST dependency discovery framework, which can provide readily consumable diagnostic information in both spatial and temporal directions. Finally, we demonstrate the utility of the proposed model, DFStrans (Diagnostic Fourier-based Spatio-temporal Transformer), in a real industrial application of building elevator control.

📄 PDF Abstract BibTeX arXiv:2305.17149

Code (0)

등록된 구현이 없습니다.

Tasks

DiagnosticTime SeriesTime Series Classification

Similar Papers 제목 키워드 기반

Encoding Agent Trajectories as Representations with Sequence Transformers

2024-10-11 · Athanasios Tsiligkaridis, Nicholas Kalinowski, Zhongheng Li, Elizabeth Hou

Spatiotemporal data faces many analogous challenges to natural language text including the ordering of locations (words) in a sequence, long range dependencies between locations, and locations having multiple meanings. I…

STPFormer: A State-of-the-Art Pattern-Aware Spatio-Temporal Transformer for Traffic Forecasting

2025-08-19 · Jiayu Fang, Zhiqi Shao, S T Boris Choy, Junbin Gao arxiv

Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often strug…

Representation LearningGraph Matching

Track Targets by Dense Spatio-Temporal Position Encoding

2022-10-17 · Jinkun Cao, Hao Wu, Kris Kitani

In this work, we propose a novel paradigm to encode the position of targets for target tracking in videos using transformers. The proposed paradigm, Dense Spatio-Temporal (DST) position encoding, encodes spatio-temporal …

Multi-Object TrackingMulti-Object Tracking and SegmentationObjectObject Tracking+1

Stecformer: Spatio-temporal Encoding Cascaded Transformer for Multivariate Long-term Time Series Forecasting

2023-05-25 · Zheng Sun, Yi Wei, Wenxiao Jia, Long Yu

Multivariate long-term time series forecasting is of great application across many domains, such as energy consumption and weather forecasting. With the development of transformer-based methods, the performance of multiv…

PredictionTime SeriesTime Series ForecastingWeather Forecasting

Supra-Laplacian Encoding for Transformer on Dynamic Graphs

2024-09-26 · Yannis Karmim, Marc Lafon, Raphael Fournier S'niehotta, Nicolas Thome

Fully connected Graph Transformers (GT) have rapidly become prominent in the static graph community as an alternative to Message-Passing models, which suffer from a lack of expressivity, oversquashing, and under-reaching…

Dynamic Link PredictionLink Prediction