arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.07495cs.CVcs.LG
收藏

一种用于静态运动发现的旋转不变隐因子模型

A Rotation Invariant Latent Factor Model for Moveme Discovery from Static Poses

California Institute of Technology(加州理工学院)

Matteo Ruggero Ronchi, Joon Sik Kim, Yisong Yue

摘要:

当训练数据由原始特征空间的低维投影组成时,我们解决了学习旋转不变潜在因子模型的问题。主要目标是发现一组3-D基本姿势,可以表征原始人类运动的流形,或movemes,从训练集的2-D投影姿势从静止图像在不同的摄像机角度。所提出的基础发现技术是数据驱动的,而不是手工设计的。学习的表示是旋转不变的,并且可以从多个视角重建任何训练实例。我们将我们的方法应用于体育运动中的人体姿势建模(通过Leeds Sports Dataset),并在一系列应用中展示了学习基础的有效性,例如活动分类,从单个帧中推断动态,以及运动的合成表示。

英文摘要:

We tackle the problem of learning a rotation invariant latent factor model when the training data is comprised of lower-dimensional projections of the original feature space. The main goal is the discovery of a set of 3-D bases poses that can characterize the manifold of primitive human motions, or movemes, from a training set of 2-D projected poses obtained from still images taken at various camera angles. The proposed technique for basis discovery is data-driven rather than hand-designed. The learned representation is rotation invariant, and can reconstruct any training instance from multiple viewing angles. We apply our method to modeling human poses in sports (via the Leeds Sports Dataset), and demonstrate the effectiveness of the learned bases in a range of applications such as activity classification, inference of dynamics from a single frame, and synthetic representation of movements.

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。

↑