适配轻量级图像计数模型的视频人群计数
Adapting Lightweight Image-based Counting Models for Video Crowd Counting
把视频中的时空信息定义为可统计解释的量，并用统计正则项在训练阶段注入，从而让任意轻量图像计数模型无需额外模块、无需多帧缓存即可获得时序增益；对做视频密集预测、想在边缘端实时部署的人，这是一个可直接套用的「训练时加正则、推理时零开销」范式。
原文依据 incorporate it into training via a statistical regularizer that effectively enhances model performance without adding modules or inference overhead
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频人群计数旨在预测视频每一帧中的人数，需要在满足实时性约束的同时有效利用视频中的时空（ST）信息。然而，现有方法大多通过辅助的提取与融合模块来利用相邻帧的时空信息，导致计算开销大，且推理时需要缓存多帧。这类设计限制了其在计算资源有限或实时性要求严格的真实应用中的实用性。为解决这些问题，我们从轻量级图像计数模型的角度重新审视视频人群计数，使模型能够在有限资源下实时部署。我们以与模型无关且具有统计可解释性的方式解析地定义时空信息，并通过统计正则项将其引入训练，从而在不增加模块、不增加推理开销的情况下有效提升模型性能。框架中的大多数超参数进一步被表述为统计推断问题，可从数据中自动估计，从而高效地适应新场景。我们的框架以紧凑且有原则的形式统一了视频人群计数与图像计数模型，具有轻量、可移植、高效的特点。我们还为将图像计数模型适配到视频人群计数建立了理论基础，并在包括具有挑战性的 DRONECROWD 和 VSCROWD 在内的六个基准上取得了最优的精度与效率。
英文原文摘要 1562 字符
Video crowd counting aims to predict the people count in each frame of a video. It requires effectively leveraging spatio-temporal (ST) information in videos while satisfying real-time constraints. However, most existing methods use ST information from neighboring frames through auxiliary extraction and fusion modules---resulting in large computational cost and the need to buffer multiple frames during inference. Such designs limit their practicality in real-world applications with limited computational resources or stringent real-time requirements. To address these issues, we revisit video crowd counting from the perspective of lightweight image-based counting models that enable real-time deployment under limited resources. We analytically define ST information in a model-independent and statistically interpretable manner, and incorporate it into training via a statistical regularizer that effectively enhances model performance without adding modules or inference overhead. Most framework hyperparameters are further formulated as statistical inference problems, allowing automatic estimation from data and consequently efficient adaptation to new scenarios.Our framework unifies video crowd counting and image-based counting models under a compact, principled formulation that is lightweight, portable, and efficient. We also establish theoretical foundations for adapting image-based counting models to video crowd counting and achieve state-of-the-art accuracy and efficiency across six benchmarks, including challenging DRONECROWD and VSCROWD.