基于黎曼流形、Fisher向量和Gestival的动作识别方法的比较评价：理想条件和非理想条件
Comparative Evaluation of Action Recognition Methods via Riemannian Manifolds, Fisher Vectors and GMMs: Ideal and Challenging Conditions
摘要：
我们提出了一个比较评估的各种技术的动作识别，同时保持尽可能多的变量控制。我们采用两类黎曼流形：对称正定矩阵和线性子空间。对于这两个类别，我们使用相应的最近邻分类器，内核，和最近的核稀疏表示。我们比较传统的动作识别技术的基础上高斯混合模型和Fisher向量（FV）。我们在理想条件下评估这些动作识别技术，以及它们在更具挑战性的条件下（尺度和平移的变化）的灵敏度。尽管最近在处理流形方面取得了进展，但基于流形的技术获得了最低的性能，并且它们的核表示在存在挑战性条件的情况下更不稳定。FV方法在理想条件下获得最高精度。此外，FV最好地处理适度的规模和翻译的变化。
英文摘要：
We present a comparative evaluation of various techniques for action recognition while keeping as many variables as possible controlled. We employ two categories of Riemannian manifolds: symmetric positive definite matrices and linear subspaces. For both categories we use their corresponding nearest neighbour classifiers, kernels, and recent kernelised sparse representations. We compare against traditional action recognition techniques based on Gaussian mixture models and Fisher vectors (FVs). We evaluate these action recognition techniques under ideal conditions, as well as their sensitivity in more challenging conditions (variations in scale and translation). Despite recent advancements for handling manifolds, manifold based techniques obtain the lowest performance and their kernel representations are more unstable in the presence of challenging conditions. The FV approach obtains the highest accuracy under ideal conditions. Moreover, FV best deals with moderate scale and translation changes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
