Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.10431 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911265720369152 |
|---|---|
| author | Perlo, Daniele Despotovic, Vladimir Boudissa, Selma Kim, Sang-Yoon Nazarov, Petr V. Zhang, Yanrong Wintermark, Max Keunen, Olivier |
| author_facet | Perlo, Daniele Despotovic, Vladimir Boudissa, Selma Kim, Sang-Yoon Nazarov, Petr V. Zhang, Yanrong Wintermark, Max Keunen, Olivier |
| contents | We introduce a curated video dataset of laboratory rodents for automatic detection of convulsive events. The dataset contains short (10~s) top-down and side-view video clips of individual rodents, labeled at clip level as normal activity or seizure. It includes 10,101 negative samples and 2,952 positive samples collected from 19 subjects. We describe the data curation, annotation protocol and preprocessing pipeline, and report baseline experiments using a transformer-based video classifier (TimeSformer). Experiments employ five-fold cross-validation with strict subject-wise partitioning to prevent data leakage (no subject appears in more than one fold). Results show that the TimeSformer architecture enables discrimination between seizure and normal activity with an average F1-score of 97%. The dataset and baseline code are publicly released to support reproducible research on non-invasive, video-based monitoring in preclinical epilepsy research. RodEpil Dataset access - DOI: 10.5281/zenodo.17601357 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10431 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RodEpil: A Video Dataset of Laboratory Rodents for Seizure Detection and Benchmark Evaluation Perlo, Daniele Despotovic, Vladimir Boudissa, Selma Kim, Sang-Yoon Nazarov, Petr V. Zhang, Yanrong Wintermark, Max Keunen, Olivier Computer Vision and Pattern Recognition We introduce a curated video dataset of laboratory rodents for automatic detection of convulsive events. The dataset contains short (10~s) top-down and side-view video clips of individual rodents, labeled at clip level as normal activity or seizure. It includes 10,101 negative samples and 2,952 positive samples collected from 19 subjects. We describe the data curation, annotation protocol and preprocessing pipeline, and report baseline experiments using a transformer-based video classifier (TimeSformer). Experiments employ five-fold cross-validation with strict subject-wise partitioning to prevent data leakage (no subject appears in more than one fold). Results show that the TimeSformer architecture enables discrimination between seizure and normal activity with an average F1-score of 97%. The dataset and baseline code are publicly released to support reproducible research on non-invasive, video-based monitoring in preclinical epilepsy research. RodEpil Dataset access - DOI: 10.5281/zenodo.17601357 |
| title | RodEpil: A Video Dataset of Laboratory Rodents for Seizure Detection and Benchmark Evaluation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.10431 |