NeuroDETR：面向异步 EEG 事件检测的多尺度离散时空 tokenization

View PDF HTML (experimental)

Abstract:Asynchronous EEG event detection supports practical brain-computer interfaces by identifying event classes and temporal boundaries directly from continuous recordings without predefined event boundaries at inference time. The primary challenge lies in extracting event-related patterns embedded in ongoing background activity. To address this, we propose \textbf{NeuroDETR}, a discrete spatiotemporal multiscale framework that combines structured tokenization with event-aware feature refinement. Multiscale temporal codebooks capture brief responses and sustained dynamics, while Spatial-Pyramid VQ hierarchically encodes spatial structure across EEG channels. These complementary representations form a compact event memory for jointly classifying events and estimating their onsets and offsets. Before tokenization, we apply FOCAL, an event-aware sparse attention module that uses predicted event presence to guide temporal feature refinement and spatial aggregation, emphasizing likely event periods while preserving context across the recording. Experiments on eight EEG datasets that span diverse paradigms demonstrate state-of-the-art performance. These findings provide a basis for the development of BCI systems that recognize meaningful neural activity during continuous interaction and monitoring.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2610.20349 [cs.LG]
	(or arXiv:2610.20349v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.20349 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yaozhi Wen [view email]
[v1] Wed, 14 Oct 2026 15:27:34 UTC (3,935 KB)