mlsanityData to 7 Oct 2026

Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction

arXiv 2603.21612 ↗First posted 23 Mar 2026cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Time series anomaly detection plays a critical role in many dynamic systems. Despite its importance, previous approaches have primarily relied on unimodal numerical data, overlooking the importance of complementary information from other modalities. In this paper, we propose a novel multimodal time series anomaly detection model (MindTS) that focuses on addressing two key challenges: (1) how to achieve semantically consistent alignment across heterogeneous multimodal data, and (2) how to filter out redundant modality information to enhance cross-modal interaction effectively. To address the first challenge, we propose Fine-grained Time-text Semantic Alignment. It integrates exogenous and endogenous text information through cross-view text fusion and a multimodal alignment mechanism, achieving semantically consistent alignment between time and text modalities. For the second challenge, we introduce Content Condenser Reconstruction, which filters redundant information within the aligned text modality and performs cross-modal reconstruction to enable interaction. Extensive experiments on six real-world multimodal datasets demonstrate that the proposed MindTS achieves competitive or superior results compared to existing methods. The code is available at: https://github.com/decisionintelligence/MindTS.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 55 of its 89 references that are in the map. First posted on arXiv 23 Mar 2026.

Builds on

55 of 89 references.

References · 55

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  4. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  5. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  6. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  7. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  8. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  9. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  10. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  11. 2023Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videoscited by 312
  12. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
38 more
  1. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 242
  2. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  3. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  4. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 172
  5. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  6. 2023UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecastingcited by 139
  7. 2022Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairscited by 130
  8. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 105
  9. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 104
  10. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  11. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 102
  12. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  13. 2025Controllable Video Generation: A Surveycited by 93
  14. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 92
  15. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 91
  16. 2025Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuningcited by 81
  17. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  18. 2024Defending Large Language Models against Jailbreak Attacks via Semantic Smoothingcited by 68
  19. 2018Precision and Recall for Time Seriescited by 67
  20. 2025Follow-Your-Creation: Empowering 4D Creation through Video Inpaintingcited by 61
  21. 2022Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Versioncited by 59
  22. 2025A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspectivecited by 58
  23. 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 58
  24. 2024TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecastingcited by 55
  25. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 54
  26. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 44
  27. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 41
  28. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 41
  29. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 37
  30. 2025Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrativecited by 35
  31. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 34
  32. 2023LightPath: Lightweight and Scalable Path Representation Learningcited by 32
  33. 2024EasyTime: Time Series Forecasting Made Easycited by 30
  34. 2025Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Controlcited by 27
  35. 2024The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embeddingcited by 26
  36. 2024Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systemscited by 25
  37. 2024MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrastcited by 18
  38. 2024Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learningcited by 16

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detectioncited by 0
  2. 2026Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoningcited by 0
  3. 2026LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detectioncited by 0