pith. sign in

arxiv: 2401.03717 · v4 · pith:NVZALBIBnew · submitted 2024-01-08 · 💻 cs.LG · cs.AI

Universal Time-Series Representation Learning: A Survey

Patara Trirat , Yooju Shin , Junhyeok Kang , Youngeun Nam , Jihye Na , Minyoung Bae , Joeun Kim , Byunghyun Kim
show 1 more author
Jae-Gil Lee
This is my paper

Pith reviewed 2026-05-24 04:24 UTC · model grok-4.3

classification 💻 cs.LG cs.AI
keywords time seriesrepresentation learningdeep learningsurveytaxonomyuniversal representationsdownstream tasks
0
0 comments X

The pith

A survey introduces a taxonomy of three fundamental elements to structure universal time-series representation learning methods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes a new taxonomy for organizing deep learning approaches to learning representations from time-series data. This taxonomy rests on three core elements that the authors identify as central to designing effective methods. By reviewing existing work through this lens, the survey highlights intuitions behind successful techniques and common experimental practices. It aims to guide future research in improving representation quality for downstream tasks across various domains. The resource link provides an updated collection of related studies.

Core claim

The authors propose a novel taxonomy based on three fundamental elements in designing state-of-the-art universal representation learning methods for time series. This framework allows a comprehensive review of existing studies, revealing how each method enhances the quality of learned representations. The survey also compiles standard experimental setups and datasets while outlining promising research directions.

What carries the argument

The novel taxonomy organized around three fundamental elements that capture the design choices in universal time-series representation learning methods.

If this is right

  • Existing methods can be systematically compared and understood through the three elements.
  • Insights from the review show specific ways methods improve representation quality.
  • Standardized experimental setups and datasets facilitate consistent evaluation.
  • Promising research directions emerge from gaps identified in the taxonomy.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Future methods might explicitly optimize for all three elements to achieve better universality.
  • The taxonomy could extend to other data modalities like images or text if similar elements apply.
  • Empirical validation of the taxonomy's completeness could involve testing against newly proposed methods.

Load-bearing premise

The three-element taxonomy captures the key design intuitions of existing and future methods without major omissions.

What would settle it

Discovery of a significant number of recent methods that cannot be classified using any of the three elements would indicate the taxonomy is incomplete.

Figures

Figures reproduced from arXiv: 2401.03717 by Byunghyun Kim, Jae-Gil Lee, Jihye Na, Joeun Kim, Junhyeok Kang, Minyoung Bae, Patara Trirat, Yooju Shin, Youngeun Nam.

Figure 1
Figure 1. Figure 1: Basic concept of time-series representation methods. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Key design elements and evaluation protocols of a time-series representation learning framework. [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Quantitative summary of the selected papers. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Illustrations of regularly and irregularly sampled multivariate time series ( [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Illustrative examples of data-centric approaches. [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Illustrative examples of neural architectural approaches. [PITH_FULL_IMAGE:figures/full_fig_p014_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Illustrative examples of learning-focused approaches. [PITH_FULL_IMAGE:figures/full_fig_p020_7.png] view at source ↗
read the original abstract

Time-series data exists in every corner of real-world systems and services, ranging from satellites in the sky to wearable devices on human bodies. Learning representations by extracting and inferring valuable information from these time series is crucial for understanding the complex dynamics of particular phenomena and enabling informed decisions. With the learned representations, we can perform numerous downstream analyses more effectively. Among several approaches, deep learning has demonstrated remarkable performance in extracting hidden patterns and features from time-series data without manual feature engineering. This survey first presents a novel taxonomy based on three fundamental elements in designing state-of-the-art universal representation learning methods for time series. According to the proposed taxonomy, we comprehensively review existing studies and discuss their intuitions and insights into how these methods enhance the quality of learned representations. Finally, as a guideline for future studies, we summarize commonly used experimental setups and datasets and discuss several promising research directions. An up-to-date corresponding resource is available at https://github.com/itouchz/awesome-deep-time-series-representations.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. This survey on universal time-series representation learning proposes a novel taxonomy organized around three fundamental elements for designing state-of-the-art methods. It reviews existing studies according to the taxonomy, discusses their intuitions and insights, summarizes commonly used experimental setups and datasets, outlines promising research directions, and provides an accompanying GitHub resource at https://github.com/itouchz/awesome-deep-time-series-representations.

Significance. If the taxonomy proves comprehensive and insightful, the survey could serve as a useful organizing framework for a rapidly expanding field. The explicit discussion of intuitions behind methods and the provision of the GitHub repository for resources and code are clear strengths that enhance accessibility and reproducibility for the community.

minor comments (3)
  1. [Abstract] Abstract: the claim of a 'novel taxonomy' would benefit from an explicit statement of how the three elements were derived or selected, even if only a short paragraph in the introduction.
  2. The manuscript should add a summary table or diagram that maps the three taxonomy elements to representative methods and their key design choices; this would improve readability without altering the central contribution.
  3. The experimental setups and datasets section would be strengthened by noting any systematic biases in the commonly used benchmarks (e.g., predominance of univariate or short-sequence data).

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of our survey, including the proposed taxonomy, discussion of intuitions, experimental summaries, and the accompanying GitHub repository. The recommendation for minor revision is noted. However, the report contains no specific major comments to address.

Circularity Check

0 steps flagged

No significant circularity; survey taxonomy has no derivation chain

full rationale

This is a literature survey paper whose central contribution is a proposed three-element taxonomy for organizing existing time-series representation learning methods, followed by a review of studies and discussion of experimental setups. No equations, predictions, fitted parameters, or mathematical derivations are present in the abstract or described content. The taxonomy is explicitly introduced as novel by the authors rather than derived from prior results or self-citations in a load-bearing way. Self-citations, if any, would be incidental to a survey and not reduce any claim to tautology. The paper is self-contained as a review with no opportunity for the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a literature survey and introduces no free parameters, mathematical axioms, or invented entities.

pith-pipeline@v0.9.0 · 5728 in / 853 out tokens · 18106 ms · 2026-05-24T04:24:42.235603+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Channel-wise Retrieval for Multivariate Time Series Forecasting

    cs.LG 2026-04 unverdicted novelty 6.0

    CRAFT improves multivariate time series forecasting accuracy by performing independent channel-wise retrieval via time-domain sparse pruning followed by frequency-domain spectral ranking.

  2. Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models

    cs.LG 2026-05 unverdicted novelty 5.0

    Self-supervised pre-training delivers large gains up to 375% on time series anomaly detection and classification but only marginal benefits for forecasting, driven by a precision-invariance trade-off in the learned re...

Reference graph

Works this paper leans on

245 extracted references · 245 canonical work pages · cited by 2 Pith papers · 8 internal anchors

  1. [1]

    Ahmed Abdulaal, Zhuanghua Liu, and Tomer Lancewicki. 2021. Practical approach to asynchronous multivariate time series anomaly detection and localization. In KDD

    work page 2021

  2. [2]

    Amine Mohamed Aboussalah, Minjae Kwon, Raj G Patel, Cheng Chi, and Chi-Guhn Lee. 2023. Recursive Time Series Data Augmentation. In ICLR

    work page 2023

  3. [3]

    Futoon M Abushaqra, Hao Xue, Yongli Ren, and Flora D Salim. 2022. CrossPyramid: Neural Ordinary Differential Equations Architecture for Partially-observed Time-series. arXiv:2212.03560 (2022)

    work page arXiv 2022

  4. [4]

    Supriya Agrahari and Anil Kumar Singh. 2022. Concept drift detection in data stream mining: A literature review. J. King Saud Univ. - Comput. Inf. Sci. 34, 10 (2022)

    work page 2022

  5. [5]

    Chuadhry Mujeeb Ahmed, Venkata Reddy Palleti, and Aditya P Mathur. 2017. WADI: a water distribution testbed for research in the design of secure cyber physical systems. In CySWater

    work page 2017

  6. [6]

    Gaurangi Anand and Richi Nayak. 2021. DeLTa: deep local pattern representation for time-series clustering and classification using visual perception. KBS 212 (2021)

    work page 2021

  7. [7]

    Ralph G Andrzejak, Klaus Lehnertz, Florian Mormann, Christoph Rieke, Peter David, and Christian E Elger. 2001. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E 64, 6 (2001)

    work page 2001

  8. [8]

    Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, Jorge Luis Reyes-Ortiz, et al. 2013. A public domain dataset for human activity recognition using smartphones.. In ESANN, Vol. 3

    work page 2013

  9. [9]

    Abdul Fatir Ansari, Alvin Heng, Andre Lim, and Harold Soh. 2023. Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series. In ICML

    work page 2023

  10. [10]

    Anthony Bagnall, Hoang Anh Dau, Jason Lines, Michael Flynn, James Large, Aaron Bostrom, Paul Southam, and Eamonn Keogh. 2018. The UEA multivariate time series classification archive, 2018. arXiv:1811.00075 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  11. [11]

    Dzmitry Bahdanau, Kyung Hyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd ICLR

    work page 2015

  12. [12]

    Shaojie Bai, J Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  13. [13]

    Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, and Mehdi Noroozi. 2021. Long short view feature decomposition via contrastive video representation learning. In ICCV. , Vol. 1, No. 1, Article . Publication date: August 2024. Universal Time-Series Representation Learning: A Survey 33

    work page 2021

  14. [14]

    Yuxuan Bian, Xuan Ju, Jiangtong Li, Zhijian Xu, Dawei Cheng, and Qiang Xu. 2024. Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning. In ICML

    work page 2024

  15. [15]

    Filippo Maria Bianchi, Lorenzo Livi, Karl Øyvind Mikalsen, Michael Kampffmeyer, and Robert Jenssen. 2019. Learning representations of multivariate time series with missing data. Pattern Recognition 96 (2019)

    work page 2019

  16. [16]

    Marin Biloš, Emanuel Ramneantu, and Stephan Günnemann. 2022. Irregularly-Sampled Time Series Modeling with Spline Networks. arXiv:2210.10630 (2022)

    work page arXiv 2022

  17. [17]

    Marin Biloš, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, and Stephan Günnemann. 2023. Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion. In ICML

    work page 2023

  18. [18]

    Ruichu Cai, Jiawei Chen, Zijian Li, Wei Chen, Keli Zhang, Junjian Ye, Zhuozhang Li, Xiaoyan Yang, and Zhenjie Zhang. 2021. Time Series Domain Adaptation via Sparse Associative Structure Alignment. In AAAI

    work page 2021

  19. [19]

    Longbing Cao. 2022. AI in Finance: Challenges, Techniques, and Opportunities. ACM CSUR 55, 3 (2022)

    work page 2022

  20. [20]

    Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu. 2018. Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8, 1 (2018)

    work page 2018

  21. [21]

    Jiawei Chen, Pengyu Song, and Chunhui Zhao. 2024. Multi-scale self-supervised representation learning with temporal alignment for multi-rate time series modeling. Pattern Recognition 145 (2024)

    work page 2024

  22. [22]

    Kaixuan Chen, Dalin Zhang, Lina Yao, Bin Guo, Zhiwen Yu, and Yunhao Liu. 2021. Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges, and Opportunities. ACM CSUR 54, 4 (2021)

    work page 2021

  23. [23]

    Ling Chen, Donghui Chen, Fan Yang, and Jianling Sun. 2021. A deep multi-task representation learning method for time series classification and retrieval. Inf. Sci. 555 (2021)

    work page 2021

  24. [24]

    Minghao Chen, Fangyun Wei, Chong Li, and Deng Cai. 2022. Frame-wise action representations for long videos via sequence contrastive learning. In CVPR

    work page 2022

  25. [25]

    Peihao Chen, Deng Huang, Dongliang He, Xiang Long, Runhao Zeng, Shilei Wen, Mingkui Tan, and Chuang Gan

    work page

  26. [26]

    RSPNet: Relative speed perception for unsupervised video representation learning. In AAAI

    work page

  27. [27]

    Ricky TQ Chen, Yulia Rubanova, Jesse Bettencourt, and David K Duvenaud. 2018. Neural ordinary differential equations. In NeurIPS

    work page 2018

  28. [28]

    Yuqi Chen, Kan Ren, Yansen Wang, Yuchen Fang, Weiwei Sun, and Dongsheng Li. 2023. ContiFormer: Continuous- Time Transformer for Irregular Time Series Modeling. In NeurIPS

    work page 2023

  29. [29]

    Yi-Chen Chen, Sung-Feng Huang, Hung-yi Lee, Yu-Hsuan Wang, and Chia-Hao Shen. 2019. Audio word2vec: Sequence-to-sequence autoencoding for unsupervised learning of audio segmentation and representation. IEEE/ACM TASLP 27, 9 (2019)

    work page 2019

  30. [30]

    Mingyue Cheng, Qi Liu, Zhiding Liu, Zhi Li, Yucong Luo, and Enhong Chen. 2023. Formertime: Hierarchical multi-scale representations for multivariate time series classification. In WWW

    work page 2023

  31. [31]

    Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  32. [32]

    Heejeong Choi and Pilsung Kang. 2023. Multi-Task Self-Supervised Time-Series Representation Learning. arXiv:2303.01034 (2023)

    work page arXiv 2023

  33. [33]

    Kukjin Choi, Jihun Yi, Changhwa Park, and Sungroh Yoon. 2021. Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines. IEEE Access (2021)

    work page 2021

  34. [34]

    Ranak Roy Chowdhury, Jiacheng Li, Xiyuan Zhang, Dezhi Hong, Rajesh Gupta, and Jingbo Shang. 2023. PrimeNet: Pre-training for Irregular Multivariate Time Series. In AAAI

    work page 2023

  35. [35]

    Ranak Roy Chowdhury, Xiyuan Zhang, Jingbo Shang, Rajesh K Gupta, and Dezhi Hong. 2022. TARNet: Task-aware reconstruction for time-series transformer. In KDD

    work page 2022

  36. [36]

    Joon Son Chung and Andrew Zisserman. 2017. Lip reading in the wild. In ACCV

    work page 2017

  37. [37]

    Gari D Clifford, Chengyu Liu, Benjamin Moody, H Lehman Li-wei, Ikaro Silva, Qiao Li, AE Johnson, and Roger G Mark

    work page

  38. [38]

    AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge

    work page

  39. [39]

    Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, et al. 2022. Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100. IJCV (2022)

    work page 2022

  40. [40]

    Hoang Anh Dau, Anthony Bagnall, Kaveh Kamgar, Chin-Chia Michael Yeh, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, and Eamonn Keogh. 2019. The UCR time series archive. IEEE JAS 6, 6 (2019)

    work page 2019

  41. [41]

    Ishan Dave, Rohit Gupta, Mamshad Nayeem Rizve, and Mubarak Shah. 2022. TCLR: Temporal contrastive learning for video representation. CVIU 219 (2022)

    work page 2022

  42. [42]

    Shohreh Deldari, Hao Xue, Aaqib Saeed, Jiayuan He, Daniel V Smith, and Flora D Salim. 2022. Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data. arXiv:2206.02353 (2022). , Vol. 1, No. 1, Article . Publication date: August 2024. 34 Trirat et al

    work page arXiv 2022

  43. [43]

    Berken Utku Demirel and Christian Holz. 2023. Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning. In NeurIPS

    work page 2023

  44. [44]

    Shuangrui Ding, Rui Qian, and Hongkai Xiong. 2022. Dual contrastive learning for spatio-temporal representation. In MM

    work page 2022

  45. [45]

    Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. 2020. The deepfake detection challenge (DFDC) dataset. arXiv:2006.07397 (2020)

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  46. [46]

    Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Yun-Zhong Qiu, Li Zhang, Jianmin Wang, and Mingsheng Long. 2024. TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling. In ICML

    work page 2024

  47. [47]

    Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang, Jianmin Wang, and Mingsheng Long. 2023. SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling. arXiv:2302.00861 (2023)

    work page arXiv 2023

  48. [48]

    Haodong Duan, Nanxuan Zhao, Kai Chen, and Dahua Lin. 2022. TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition. In CVPR

    work page 2022

  49. [49]

    Jufang Duan, Wei Zheng, Yangzhou Du, Wenfa Wu, Haipeng Jiang, and Hongsheng Qi. 2024. MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series. In ICML

    work page 2024

  50. [50]

    Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, and Xiaoli Li. 2023. Label-efficient time series representation learning: A review. arXiv:2302.06433 (2023)

    work page arXiv 2023

  51. [51]

    Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, and Cuntai Guan. 2021. Time-Series Representation Learning via Temporal and Contextual Contrasting. In IJCAI

    work page 2021

  52. [52]

    Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, and Xiaoli Li. 2024. TSLANet: Rethinking Trans- formers for Time Series Representation Learning. In ICML

    work page 2024

  53. [53]

    Dave Epstein, Boyuan Chen, and Carl Vondrick. 2020. Oops! predicting unintentional action in video. In CVPR

    work page 2020

  54. [54]

    Linus Ericsson, Henry Gouk, Chen Change Loy, and Timothy M Hospedales. 2022. Self-supervised representation learning: Introduction, advances, and challenges. IEEE Signal Process. Mag. 39, 3 (2022)

    work page 2022

  55. [55]

    Arik Ermshaus, Patrick Schäfer, and Ulf Leser. 2023. ClaSP: parameter-free time series segmentation. DMKD (2023)

    work page 2023

  56. [56]

    Philippe Esling and Carlos Agon. 2012. Time-Series Data Mining. ACM CSUR 45, 1 (2012)

    work page 2012

  57. [57]

    Yuchen Fang, Kan Ren, Caihua Shan, Yifei Shen, You Li, Weinan Zhang, Yong Yu, and Dongsheng Li. 2023. Learning decomposed spatial relations for multi-variate time-series modeling. In AAAI

    work page 2023

  58. [58]

    Yasmin Fathy, Payam Barnaghi, and Rahim Tafazolli. 2018. Large-Scale Indexing, Discovery, and Ranking for the Internet of Things (IoT). ACM CSUR 51, 2 (2018)

    work page 2018

  59. [59]

    Elizabeth Fons, Alejandro Sztrajman, Yousef El-Laham, Alexandros Iosifidis, and Svitlana Vyetrenko. 2022. HyperTime: Implicit Neural Representations for Time Series. In NeurIPS SyntheticData4ML Workshop

    work page 2022

  60. [60]

    Navid Mohammadi Foumani, Lynn Miller, Chang Wei Tan, Geoffrey I Webb, Germain Forestier, and Mahsa Salehi

    work page

  61. [61]

    arXiv:2302.02515 (2023)

    Deep learning for time series classification and extrinsic regression: A current survey. arXiv:2302.02515 (2023)

    work page arXiv 2023

  62. [62]

    Archibald Fraikin, Adrien Bennetot, and Stéphanie Allassonnière. 2023. T-Rep: Representation Learning for Time Series using Time-Embeddings. arXiv:2310.04486 (2023)

    work page arXiv 2023

  63. [63]

    Jean-Yves Franceschi, Aymeric Dieuleveut, and Martin Jaggi. 2019. Unsupervised Scalable Representation Learning for Multivariate Time Series. In NeurIPS

    work page 2019

  64. [64]

    Shanghua Gao, Teddy Koker, Owen Queen, Thomas Hartvigsen, Theodoros Tsiligkaridis, and Marinka Zitnik. 2024. UniTS: Building a Unified Time Series Model. arXiv:2403.00131 (2024)

    work page arXiv 2024

  65. [65]

    Wenbo Ge, Pooia Lalbakhsh, Leigh Isai, Artem Lenskiy, and Hanna Suominen. 2022. Neural Network–Based Financial Volatility Forecasting: A Systematic Review. ACM CSUR 55, 1 (2022)

    work page 2022

  66. [66]

    Shaghayegh Gharghabi, Yifei Ding, Chin-Chia Michael Yeh, Kaveh Kamgar, Liudmila Ulanova, and Eamonn Keogh

    work page

  67. [67]

    Matrix profile VIII: domain agnostic online semantic segmentation at superhuman performance levels. In ICDM

    work page

  68. [68]

    Jairo Giraldo, David Urbina, Alvaro Cardenas, Junia Valente, Mustafa Faisal, Justin Ruths, Nils Ole Tippenhauer, Henrik Sandberg, and Richard Candell. 2018. A Survey of Physics-Based Attack Detection in Cyber-Physical Systems. ACM CSUR 51, 4 (2018)

    work page 2018

  69. [69]

    Rakshitha Wathsadini Godahewa, Christoph Bergmeir, Geoffrey I Webb, Rob Hyndman, and Pablo Montero-Manso

    work page

  70. [70]

    In NeurIPS

    Monash Time Series Forecasting Archive. In NeurIPS

    work page

  71. [71]

    Yoav Goldberg and Omer Levy. 2014. word2vec Explained: deriving Mikolov et al. ’s negative-sampling word- embedding method. arXiv:1402.3722 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  72. [72]

    Matt Gorbett, Hossein Shirazi, and Indrakshi Ray. 2023. Sparse Binary Transformers for Multivariate Time Series Modeling. In KDD

    work page 2023

  73. [73]

    Mononito Goswami, Konrad Szafer, Arjun Choudhry, Yifu Cai, Shuo Li, and Artur Dubrawski. 2024. MOMENT: A Family of Open Time-series Foundation Models. In ICML

    work page 2024

  74. [74]

    Fuqiang Gu, Mu-Huan Chung, Mark Chignell, Shahrokh Valaee, Baoding Zhou, and Xue Liu. 2021. A Survey on Deep Learning for Human Activity Recognition. ACM CSUR 54, 8 (2021). , Vol. 1, No. 1, Article . Publication date: August 2024. Universal Time-Series Representation Learning: A Survey 35

    work page 2021

  75. [75]

    Sheng Guo, Zihua Xiong, Yujie Zhong, Limin Wang, Xiaobo Guo, Bing Han, and Weilin Huang. 2022. Cross-architecture self-supervised video representation learning. In CVPR

    work page 2022

  76. [76]

    Xudong Guo, Xun Guo, and Yan Lu. 2021. SSAN: Separable self-attention network for video representation learning. In CVPR

    work page 2021

  77. [77]

    Isma Hadji, Konstantinos G Derpanis, and Allan D Jepson. 2021. Representation learning via global temporal alignment and cycle-consistency. In CVPR

    work page 2021

  78. [78]

    Ainaz Hajimoradlou, Leila Pishdad, Frederick Tung, and Maryna Karpusha. 2022. Self-Supervised Time Series Representation Learning with Temporal-Instance Similarity Distillation. In ICML Pre-training Workshop

    work page 2022

  79. [79]

    Tengda Han, Weidi Xie, and Andrew Zisserman. 2020. Memory-augmented dense predictive coding for video representation learning. In ECCV

    work page 2020

  80. [80]

    Sanjay Haresh, Sateesh Kumar, Huseyin Coskun, Shahram N Syed, Andrey Konin, Zeeshan Zia, and Quoc-Huy Tran

    work page

Showing first 80 references.