RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization

2026-03-24

AI Summary

This work addresses the limitations of existing research on rat epileptic behavior analysis, which has been hindered by the absence of precisely annotated temporal labels and standardized evaluation protocols. To bridge this gap, we introduce RatSeizure, the first publicly available fine-grained benchmark dataset for rat epileptic behaviors, featuring detailed temporal boundary annotations and action unit labels. We further propose RaSeformer, a novel Transformer-based architecture that integrates saliency-aware mechanisms with contextual modeling for simultaneous epileptic behavior classification and temporal localization. By establishing standardized data splits and evaluation protocols, RaSeformer achieves state-of-the-art performance on RatSeizure, offering the community a reproducible strong baseline and a unified framework for future research in this domain.

Abstract

Animal models, particularly rats, play a critical role in seizure research for studying epileptogenesis and treatment response. However, progress is limited by the lack of datasets with precise temporal annotations and standardized evaluation protocols. Existing animal behavior datasets often have limited accessibility, coarse labeling, and insufficient temporal localization of clinically meaningful events. To address these limitations, we introduce RatSeizure, the first publicly benchmark for fine-grained seizure behavior analysis. The dataset consists of recorded clips annotated with seizure-related action units and temporal boundaries, enabling both behavior classification and temporal localization. We further propose RaSeformer, a saliency-context Transformer for temporal action localization that highlights behavior-relevant context while suppressing redundant cues. Experiments on RatSeizure show that RaSeformer achieves strong performance and provides a competitive reference model for this challenging task. We also establish standardized dataset splits and evaluation protocols to support reproducible benchmarking.

Problem

• rat seizure
• temporal localization
• behavior annotation
• benchmark dataset
• epilepsy research

Innovation

• RatSeizure
• temporal action localization
• saliency-context Transformer
• epileptic seizure
• benchmark dataset