{"ID":2896123,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07734","arxiv_id":"2507.07734","title":"EEvAct: Early Event-Based Action Recognition with High-Rate Two-Stream Spiking Neural Networks","abstract":"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.","short_abstract":"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 ev...","url_abs":"https://arxiv.org/abs/2507.07734","url_pdf":"https://arxiv.org/pdf/2507.07734v1","authors":"[\"Michael Neumeier\",\"Jules Lecomte\",\"Nils Kazinski\",\"Soubarna Banik\",\"Bing Li\",\"Axel von Arnim\"]","published":"2025-07-10T13:13:53Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.NE\"]","methods":"[]","has_code":false}