用高频率脉冲网络实现早期动作识别，精度提升2%。
EEvAct: Early Event-Based Action Recognition with High-Rate Two-Stream Spiking Neural Networks
- 设计双流脉冲神经网络，直接处理高频率事件数据。
- 在THU EACT-50数据集上准确率领先前人2%。
- 适用于体育动作捕捉等需要快速响应的实时场景。
早期识别人类动作对人机与人机交互的安全性与响应速度至关重要。由于事件视觉传感器具有高时间分辨率和低延迟特性，非常适配早期识别需求。然而，现有方法多将事件累积为低频帧或时空体素，限制了早期预测能力。相比之下，脉冲神经网络（SNN）可直接处理高频率事件以实现早期预测，但多数工作仍难以兼顾最终精度。本文提出一种高频率双流SNN，在大规模THU EACT-50数据集上相较之前方法提升2%的最终准确率。我们通过新构建的早期事件识别框架，报告了随观察时间增长的Top-1与Top-5识别得分。最后，展示了该方法在体育运动捕捉中实现早期动作触发的实际应用效果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。