Abstract
Integrating local spatial-temporal patterns with global temporal dependencies under EEG non-stationarity remains challenging for motor-imagery BCIs. We propose EEG-LoGNet, a compact dual-stream architecture fusing multi-scale local encoding with adaptive global modeling via confidence-routed gating, achieving 87.20% subject-specific accuracy with only ~35k parameters on BCI Competition IV-2a.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MLCN_2026_041.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=ZTiz24DWm7
BibTex
@InProceedings{GuoJin_EEGLoGNet_MICCAISAT2026,
author = { Guo, Jinsong AND Li, Yuchong AND Jia, Fucang},
title = { { EEG-LoGNet: Bridging Local Features and Global Contexts for EEG-Based Motor Imagery Classification } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17255},
month = {pending},
page = {pending}
}