# Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures

arXiv: https://arxiv.org/abs/2106.12014 · HTML: https://mlsanity.com/paper/2106.12014/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Large-scale weakly-supervised pre-training for video action recognition](https://mlsanity.com/paper/1905.00561/) (2019)
- [Accuracy and Performance Comparison of Video Action Recognition Approaches](https://mlsanity.com/paper/2008.09037/) (2020)

## Built on by (most cited first, 7 of 7)

- [Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography](https://mlsanity.com/paper/2207.01391/) (2022)
- [Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations](https://mlsanity.com/paper/2203.01933/) (2022)
- [Privacy-preserving Early Detection of Epileptic Seizures in Videos](https://mlsanity.com/paper/2309.08794/) (2023)
- [Deep Learning Approaches for Seizure Video Analysis: A Review](https://mlsanity.com/paper/2312.10930/) (2023)
- [VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG](https://mlsanity.com/paper/2311.14775/) (2023)
- [Forecasting Epileptic Seizures from Contactless Camera via Cross-Species Transfer Learning](https://mlsanity.com/paper/2603.12887/) (2026)
- [A Neurosymbolic Framework for Interpretable Skeleton-Based Seizure Detection via Concept-Driven Logical Reasoning](https://mlsanity.com/paper/2606.21252/) (2026)

## Abstract (arXiv)

Detailed analysis of seizure semiology, the symptoms and signs which occur during a seizure, is critical for management of epilepsy patients. Inter-rater reliability using qualitative visual analysis is often poor for semiological features. Therefore, automatic and quantitative analysis of video-recorded seizures is needed for objective assessment. We present GESTURES, a novel architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to learn deep representations of arbitrarily long videos of epileptic seizures. We use a spatiotemporal CNN (STCNN) pre-trained on large human action recognition (HAR) datasets to extract features from short snippets (approx. 0.5 s) sampled from seizure videos. We then train an RNN to learn seizure-level representations from the sequence of features. We curated a dataset of seizure videos from 68 patients and evaluated GESTURES on its ability to classify seizures into focal onset seizures (FOSs) (N = 106) vs. focal to bilateral tonic-clonic seizures (TCSs) (N = 77), obtaining an accuracy of 98.9% using bidirectional long short-term memory (BLSTM) units. We demonstrate that an STCNN trained on a HAR dataset can be used in combination with an RNN to accurately represent arbitrarily long videos of seizures. GESTURES can provide accurate seizure classification by modeling sequences of semiologies.