mlsanityData to 7 Oct 2026

TimeNet: Pre-trained deep recurrent neural network for time series classification

arXiv 1706.08838 ↗First posted 23 Jun 2017cs.LGcited by 46

Not on the map. Why?

Abstract (arXiv)

Inspired by the tremendous success of deep Convolutional Neural Networks as generic feature extractors for images, we propose TimeNet: a deep recurrent neural network (RNN) trained on diverse time series in an unsupervised manner using sequence to sequence (seq2seq) models to extract features from time series. Rather than relying on data from the problem domain, TimeNet attempts to generalize time series representation across domains by ingesting time series from several domains simultaneously. Once trained, TimeNet can be used as a generic off-the-shelf feature extractor for time series. The representations or embeddings given by a pre-trained TimeNet are found to be useful for time series classification (TSC). For several publicly available datasets from UCR TSC Archive and an industrial telematics sensor data from vehicles, we observe that a classifier learned over the TimeNet embeddings yields significantly better performance compared to (i) a classifier learned over the embeddings given by a domain-specific RNN, as well as (ii) a nearest neighbor classifier based on Dynamic Time Warping.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 7; 2023: 14; 2024: 6; 2025: 3; 2026: 4.

46 papers.

Sort:

  1. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  2. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
  3. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  4. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  5. 2021Chaos as an interpretable benchmark for forecasting and data-driven modellingcited by 87
  6. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  7. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  8. 2023TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learningcited by 51
  9. 2023TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoderscited by 42
  10. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  11. 2022MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Seriescited by 28
  12. 2021A comparison of LSTM and GRU networks for learning symbolic sequencescited by 24
34 more
  1. 2023T-Rep: Representation Learning for Time Series using Time-Embeddingscited by 19
  2. 2023CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detectioncited by 15
  3. 2022Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensionscited by 14
  4. 2023Unsupervised Representation Learning for Time Series: A Reviewcited by 14
  5. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Maskcited by 10
  6. 2022Unsupervised pre-training of graph transformers on patient population graphscited by 9
  7. 2024Efficient High-Resolution Time Series Classification via Attention Kronecker Decompositioncited by 5
  8. 2024EMIT- Event-Based Masked Auto Encoding for Irregular Time Seriescited by 5
  9. 2021FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variationscited by 4
  10. 2022Face Forgery Detection Based on Facial Region Displacement Trajectory Seriescited by 4
  11. 2021Computer Vision Self-supervised Learning Methods on Time Seriescited by 3
  12. 2021Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!cited by 3
  13. 2023Self-Distilled Representation Learning for Time Seriescited by 3
  14. 2025SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecastingcited by 3
  15. 2021A Self-Supervised Framework for Function Learning and Extrapolationcited by 2
  16. 2022Spectral Propagation Graph Network for Few-shot Time Series Classificationcited by 2
  17. 2023Anamnesic Neural Differential Equations with Orthogonal Polynomial Projectionscited by 2
  18. 2024Aircraft Trajectory Segmentation-based Contrastive Coding: A Framework for Self-supervised Trajectory Representationcited by 2
  19. 2021Pattern Discovery in Time Series with Byte Pair Encodingcited by 1
  20. 2021Predicting the outcome of team movements -- Player time series analysis using fuzzy and deep methods for representation learningcited by 1
  21. 2022Forecasting the abnormal events at well drilling with machine learningcited by 1
  22. 2023Domain-invariant Clinical Representation Learning by Bridging Data Distribution Shift across EMR Datasetscited by 1
  23. 2024On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approachcited by 1
  24. 2024Low-Power Vibration-Based Predictive Maintenance for Industry 4.0 using Neural Networks: A Surveycited by 1
  25. 2021Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Modelscited by 0
  26. 2021Predictive Auto-scaling with OpenStack Monascacited by 0
  27. 2023Interpretable time series neural representation for classification purposescited by 0
  28. 2023Unsupervised Multi-modal Feature Alignment for Time Series Representation Learningcited by 0
  29. 2025MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learningcited by 0
  30. 2025Hybrid Autoencoder-Based Framework for Early Fault Detection in Wind Turbinescited by 0
  31. 2026An Exploratory Study to Repurpose LLMs to a Unified Architecture for Time Series Classificationcited by 0
  32. 2026SEAnet: A Deep Learning Architecture for Data Series Similarity Searchcited by 0
  33. 2026Is Self-Pretraining really useful to improve diagnosis in medical Time Series?cited by 0
  34. 2026SMart: A Multi-source Multi-phase Time Series Representation Transfer Frameworkcited by 0