EEvAct: Early Event-Based Action Recognition with High-Rate Two-Stream Spiking Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913936290349056 |
|---|---|
| author | Neumeier, Michael Lecomte, Jules Kazinski, Nils Banik, Soubarna Li, Bing von Arnim, Axel |
| author_facet | Neumeier, Michael Lecomte, Jules Kazinski, Nils Banik, Soubarna Li, Bing von Arnim, Axel |
| contents | Recognizing human activities early is crucial for the safety and responsiveness of human-robot and human-machine interfaces. Due to their high temporal resolution and low latency, event-based vision sensors are a perfect match for this early recognition demand. However, most existing processing approaches accumulate events to low-rate frames or space-time voxels which limits the early prediction capabilities. In contrast, spiking neural networks (SNNs) can process the events at a high-rate for early predictions, but most works still fall short on final accuracy. In this work, we introduce a high-rate two-stream SNN which closes this gap by outperforming previous work by 2% in final accuracy on the large-scale THU EACT-50 dataset. We benchmark the SNNs within a novel early event-based recognition framework by reporting Top-1 and Top-5 recognition scores for growing observation time. Finally, we exemplify the impact of these methods on a real-world task of early action triggering for human motion capture in sports. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EEvAct: Early Event-Based Action Recognition with High-Rate Two-Stream Spiking Neural Networks Neumeier, Michael Lecomte, Jules Kazinski, Nils Banik, Soubarna Li, Bing von Arnim, Axel Computer Vision and Pattern Recognition Neural and Evolutionary Computing Recognizing human activities early is crucial for the safety and responsiveness of human-robot and human-machine interfaces. Due to their high temporal resolution and low latency, event-based vision sensors are a perfect match for this early recognition demand. However, most existing processing approaches accumulate events to low-rate frames or space-time voxels which limits the early prediction capabilities. In contrast, spiking neural networks (SNNs) can process the events at a high-rate for early predictions, but most works still fall short on final accuracy. In this work, we introduce a high-rate two-stream SNN which closes this gap by outperforming previous work by 2% in final accuracy on the large-scale THU EACT-50 dataset. We benchmark the SNNs within a novel early event-based recognition framework by reporting Top-1 and Top-5 recognition scores for growing observation time. Finally, we exemplify the impact of these methods on a real-world task of early action triggering for human motion capture in sports. |
| title | EEvAct: Early Event-Based Action Recognition with High-Rate Two-Stream Spiking Neural Networks |
| topic | Computer Vision and Pattern Recognition Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2507.07734 |