用RGB图像模拟光流，实时检测动作且速度快。
CAKE: Real-time Action Detection via Motion Distillation and Background-aware Contrastive Learning
- 通过动态适配器提取运动特征，无需计算光流。
- 在多个数据集上达到领先性能，同时保持72帧以上速度。
- 适合部署在资源受限的实时系统中。
在线动作检测系统面临两大挑战：计算成本高，以及对背景运动中区分性时序动态建模不足。添加光流可提供强运动线索，但带来显著计算开销。我们提出CAKE，一种基于光流的知识蒸馏框架，将运动知识迁移到仅使用RGB的模型中。提出动态运动适配器（DMA），抑制静态背景噪声，突出像素变化，有效逼近光流而无需显式计算。框架还集成浮动对比学习策略，以区分信息性运动动态与时序背景。在TVSeries、THUMOS'14、Kinetics-400数据集上的实验表明，该模型在使用相同主干网络的情况下，实现了卓越的平均精度（mAP）。模型在单个CPU上运行速度超过72 FPS，非常适合资源受限的系统。
原文摘要 · Abstract (English)
Online Action Detection (OAD) systems face two primary challenges: high computational cost and insufficient modeling of discriminative temporal dynamics against background motion. Adding optical flow could provides strong motion cues but it incurs significant computational overhead. We propose CAKE, a OAD Flow-based distillation framework to transfer motion knowledge into RGB models. We propose Dynamic Motion Adapter (DMA) to suppress static background noise and emphasize pixel changes, effectively approximating optical flow without explicit computation. The framework also integrates a Floating Contrastive Learning strategy to distinguish informative motion dynamics from temporal background. Various experiments conducted on the TVSeries, THUMOS'14, Kinetics-400 datasets show effectiveness of our model. CAKE achieves a standout mAP compared with SOTA while using the same backbone. Our model operates at over 72 FPS on a single CPU, making it highly suitable for resource-constrained systems.
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。