# HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding

arXiv: https://arxiv.org/abs/2601.12279 · HTML: https://mlsanity.com/paper/2601.12279/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 46 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Transformers without Normalization](https://mlsanity.com/paper/2503.10622/) (2025)
- [Multi-Scale Neural network for EEG Representation Learning in BCI](https://mlsanity.com/paper/2003.02657/) (2020)
- [Efficacy of Transformer Networks for Classification of Raw EEG Data](https://mlsanity.com/paper/2202.05170/) (2022)
- [Dual-TSST: A Dual-Branch Temporal-Spectral-Spatial Transformer Model for EEG Decoding](https://mlsanity.com/paper/2409.03251/) (2024)
- [Binary Single-dimensional Convolutional Neural Network for Seizure Prediction](https://mlsanity.com/paper/2206.07518/) (2022)
- [Foundation Models for Cross-Domain EEG Analysis Application: A Survey](https://mlsanity.com/paper/2508.15716/) (2025)
- [Transformer-based EEG Decoding: A Survey](https://mlsanity.com/paper/2507.02320/) (2025)

## Abstract (arXiv)

Electroencephalography (EEG) decoding requires models that can effectively extract and integrate complex temporal, spectral, and spatial features from multichannel signals. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time-space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages, while a customized Dynamic Tanh normalization module is introduced to replace traditional Layer Normalization in order to enhance training stability and reduce redundancy. Extensive experiments are conducted on two representative benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related cross-subject classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm that each core component of the proposed framework contributes significantly to the overall decoding performance, demonstrating HCFT's effectiveness in capturing EEG dynamics and its potential for real-world BCI applications.