Time Series Classification

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

52 leaderboard tables shown for this task, 52 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 52 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

19 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 328 papers with code (697 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
  20 Nov 2016 12 repositories listed Syntology ran 1 of 10 samples · 9 unverified · 1 pointer-only (licence)
  We propose a simple but strong baseline for time series classification from scratch with deep neural networks.
• Latent ODEs for Irregularly-Sampled Time Series
  8 Jul 2019 11 repositories listed Syntology ran 4 of 8 samples · 4 unverified · 3 pointer-only (licence)
  Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs).
• InceptionTime: Finding AlexNet for Time Series Classification
  11 Sep 2019 10 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  TSC is the area of machine learning tasked with the categorization (or labelling) of time series.
• LSTM Fully Convolutional Networks for Time Series Classification
  8 Sep 2017 9 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification.
• LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
  1 Jul 2016 8 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine.
• Multivariate LSTM-FCNs for Time Series Classification
  14 Jan 2018 7 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Over the past decade, multivariate time series classification has received great attention.
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
  6 Jun 2016 7 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 2 pointer-only (licence)
  Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values.
• A Transformer-based Framework for Multivariate Time Series Representation Learning
  6 Oct 2020 6 repositories listed Syntology ran 5 of 32 samples · 27 unverified · 2 pointer-only (licence)
  In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series.
• ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
  29 Oct 2019 6 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger…
• Deep learning for time series classification: a review
  12 Sep 2018 6 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC.
• Proximity Forest: An effective and scalable distance-based classifier for time series
  31 Aug 2018 6 repositories listed
  We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models…
• PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series
  30 May 2023 5 repositories listed Syntology ran 0 of 21 samples · 21 unverified
  PyPOTS is an open-source Python library dedicated to data mining and analysis on multivariate partially-observed time series, i.
• TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
  1 Mar 2023 5 repositories listed
  In this work, we propose TimeMAE, a novel self-supervised paradigm for learning transferrable time series representations based on transformer networks.
• Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices
  1 Dec 2019 5 repositories listed
  The second layer consumes the output of the first layer using a second RNN thus capturing long dependencies.
• Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
  19 Mar 2024 4 repositories listed
  To address this challenge, we propose CrossTimeNet, a novel cross-domain SSL learning framework to learn transferable knowledge from various domains to largely benefit the target downstream task.
• Advancing Time Series Classification with Multimodal Language Modeling
  19 Mar 2024 4 repositories listed
  In this work, we propose InstructTime, a novel attempt to reshape time series classification as a learning-to-generate paradigm.
• TS2Vec: Towards Universal Representation of Time Series
  19 Jun 2021 4 repositories listed Syntology ran 11 of 23 samples · 12 unverified
  Furthermore, to obtain the representation of an arbitrary sub-sequence in the time series, we can apply a simple aggregation over the representations of corresponding timestamps.
• Neural Rough Differential Equations for Long Time Series
  17 Sep 2020 4 repositories listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  Neural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuous-time way to model functions…
• The Signature Kernel is the solution of a Goursat PDE
  26 Jun 2020 4 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  Recently, there has been an increased interest in the development of kernel methods for learning with sequential data.
• Insights into LSTM Fully Convolutional Networks for Time Series Classification
  27 Feb 2019 4 repositories listed
  In this paper, we perform a series of ablation tests (3627 experiments) on LSTM-FCN and ALSTM-FCN to provide a better understanding of the model and each of its sub-module.
• Precision and Recall for Time Series
  8 Mar 2018 4 repositories listed
  Classical anomaly detection is principally concerned with point-based anomalies, those anomalies that occur at a single point in time.
• Imaging Time-Series to Improve Classification and Imputation
  1 Jun 2015 4 repositories listed
  We used Tiled Convolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn high-level features from the individual and compound GASF-GADF-MTF images.
• CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models
  24 May 2024 3 repositories listed
  Despite the excelling performance of machine learning models, understanding the decisions of machine learning models remains a long-standing goal.
• TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
  6 May 2024 3 repositories listed Syntology ran 6 of 12 samples · 6 unverified · 1 pointer-only (licence)
  Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC).
• Bake off redux: a review and experimental evaluation of recent time series classification algorithms
  25 Apr 2023 3 repositories listed
  We introduce 30 classification datasets either recently donated to the archive or reformatted to the TSC format, and use these to further evaluate the best performing algorithm from each category.
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification
  20 Feb 2023 3 repositories listed
  Deep learning-based algorithms, e.
• SAITS: Self-Attention-based Imputation for Time Series
  17 Feb 2022 3 repositories listed Syntology ran 3 of 10 samples · 7 unverified
  Missing data in time series is a pervasive problem that puts obstacles in the way of advanced analysis.
• Voice2Series: Reprogramming Acoustic Models for Time Series Classification
  17 Jun 2021 3 repositories listed Syntology ran 1 of 7 samples · 6 unverified · 3 pointer-only (licence)
  Learning to classify time series with limited data is a practical yet challenging problem.
• Bearing Fault Diagnosis Base on Multi-scale CNN and LSTM Model
  5 Jun 2020 3 repositories listed
  Intelligent fault diagnosis methods based on signal analysis have been widely used for bearing fault diagnosis.
• Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
  24 Feb 2020 3 repositories listed Syntology ran 7 of 11 samples · 4 unverified · 3 pointer-only (licence)
  Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multiple prime numbers according to the length of the time series.

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.