# Learning Cross-Joint Attention for Generalizable Video-Based Seizure Detection

arXiv: https://arxiv.org/abs/2603.23757 · HTML: https://mlsanity.com/paper/2603.23757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 24 Mar 2026.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Privacy-preserving Early Detection of Epileptic Seizures in Videos](https://mlsanity.com/paper/2309.08794/) (2023)
- [VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG](https://mlsanity.com/paper/2311.14775/) (2023)

## Abstract (arXiv)

Automated seizure detection from long-term clinical videos can substantially reduce manual review time and enable real-time monitoring. However, existing video-based methods often struggle to generalize to unseen subjects due to background bias and reliance on subject-specific appearance cues. We propose a joint-centric attention model that focuses exclusively on body dynamics to improve cross-subject generalization. For each video segment, body joints are detected and joint-centered clips are extracted, suppressing background context. These joint-centered clips are tokenized using a Video Vision Transformer (ViViT), and cross-joint attention is learned to model spatial and temporal interactions between body parts, capturing coordinated movement patterns characteristic of seizure semiology. Extensive cross-subject experiments show that the proposed method consistently outperforms state-of-the-art CNN-, graph-, and transformer-based approaches on unseen subjects.