mlsanityData to 14 Oct 2026

BolT: Fused Window Transformers for fMRI Time Series Analysis

arXiv 2205.11578 ↗First posted 23 May 2022eess.SP cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time scales. Here, we present BolT, a blood-oxygen-level-dependent transformer model, for analyzing multi-variate fMRI time series. BolT leverages a cascade of transformer encoders equipped with a novel fused window attention mechanism. Encoding is performed on temporally-overlapped windows within the time series to capture local representations. To integrate information temporally, cross-window attention is computed between base tokens in each window and fringe tokens from neighboring windows. To gradually transition from local to global representations, the extent of window overlap and thereby number of fringe tokens are progressively increased across the cascade. Finally, a novel cross-window regularization is employed to align high-level classification features across the time series. Comprehensive experiments on large-scale public datasets demonstrate the superior performance of BolT against state-of-the-art methods. Furthermore, explanatory analyses to identify landmark time points and regions that contribute most significantly to model decisions corroborate prominent neuroscientific findings in the literature.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 33 of its 152 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

33 of 152 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2020Longformer: The Long-Document Transformercited by 3,413
  8. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  9. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  10. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 320
  11. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288
  12. 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
21 more
  1. 2018Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Diseasecited by 99
  2. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 87
  3. 2021Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformerscited by 77
  4. 2020Spatio-Temporal Graph Convolution for Resting-State fMRI Analysiscited by 57
  5. 2018Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networkscited by 43
  6. 2017Spectral Graph Convolutions for Population-based Disease Predictioncited by 42
  7. 2020Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysiscited by 41
  8. 2019Graph Neural Network for Interpreting Task-fMRI Biomarkerscited by 40
  9. 2022Federated Learning of Generative Image Priors for MRI Reconstructioncited by 33
  10. 2016Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based examplecited by 31
  11. 2018Graph Saliency Maps through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivitycited by 21
  12. 2019Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networkscited by 20
  13. 2018Deep Learning with Mixed Supervision for Brain Tumor Segmentationcited by 18
  14. 2021TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imagingcited by 18
  15. 2020Attend and Decode: 4D fMRI Task State Decoding Using Attention Modelscited by 17
  16. 2017Resting state fMRI functional connectivity-based classification using a convolutional neural network architecturecited by 11
  17. 2016Classification of Alzheimer's Disease using fMRI Data and Deep Learning Convolutional Neural Networkscited by 8
  18. 2015Deep learning of fMRI big data: a novel approach to subject-transfer decodingcited by 7
  19. 2018Brain Age Prediction Based on Resting-State Functional Connectivity Patterns Using Convolutional Neural Networkscited by 7
  20. 2022Disentangling Spatial-Temporal Functional Brain Networks via Twin-Transformerscited by 6
  21. 2017Learning Neural Representations of Human Cognition across Many fMRI Studiescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 6; 2025: 6; 2026: 4.

23 papers.

Sort:

By area:

  1. 2023SwiFT: Swin 4D fMRI Transformercited by 36
  2. 2022Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectivescited by 33
  3. 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
  4. 2023DreaMR: Diffusion-driven Counterfactual Explanation for Functional MRIcited by 14
  5. 2025fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understandingcited by 7
  6. 2023HydraViT: Adaptive Multi-Branch Transformer for Multi-Label Disease Classification from Chest X-ray Imagescited by 6
  7. 2024NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomescited by 6
  8. 2025Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Modelcited by 4
  9. 2023MCI Detection using fMRI time series embeddings of Recurrence plotscited by 3
  10. 2026NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoningcited by 3
  11. 2024Machine Learning on Dynamic Functional Connectivity: Promise, Pitfalls, and Interpretationscited by 2
  12. 2024STARFormer: A Novel Spatio-Temporal Aggregation Reorganization Transformer of FMRI for Brain Disorder Diagnosiscited by 2
11 more
  1. 2025Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantizationcited by 2
  2. 2025Resting-state fMRI Analysis using Quantum Time-series Transformercited by 1
  3. 2025VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRIcited by 1
  4. 2023Self-Supervised Pretraining on Paired Sequences of fMRI Data for Transfer Learning to Brain Decoding Taskscited by 0
  5. 2023Sequential Transfer Learning to Decode Heard and Imagined Timbre from fMRI Datacited by 0
  6. 2024Reconstructing physiological signals from fMRI across the adult lifespancited by 0
  7. 2024Multi-Task Adversarial Variational Autoencoder for Estimating Biological Brain Age with Multimodal Neuroimagingcited by 0
  8. 2025Deep Learning Inductive Biases for fMRI Time Series Classification during Resting-state and Movie-watchingcited by 0
  9. 2026NeuroSSM: Multiscale Differential State-Space Modeling for Context-Aware fMRI Analysiscited by 0
  10. 2026Nonlocal operator learning for fMRI encoding and decoding taskscited by 0
  11. 2026UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learningcited by 0