论文标题
通过未经训练的发电机网络的潜在空间分离，用于隔离视频数据中的不同运动类型
Latent-space disentanglement with untrained generator networks for the isolation of different motion types in video data
论文作者
论文摘要
在视频分析中，隔离视频数据中不同类型的运动是一个高度相关的问题。例如，在动态医学或生物成像中可以找到应用，在这种动态医学或生物学成像中，在其中的分析和进一步处理感兴趣的动态通常会因测量主体的运动而复杂化。在这项工作中，经验表明，通过未经训练的生成器网络的视频数据表示，以及一种针对潜在空间分离的特定技术，该技术对某些基本动力学的使用最少，一维信息，允许有效地分离出不同的，高度非线性的运动类型。特别是，这样的表示允许冻结任何选择运动类型，并获得其他感兴趣动态的准确独立表示。获得此类表示形式不需要在训练数据集上进行任何预训练，即发电机网络的所有参数直接从单个视频中学习。
Isolating different types of motion in video data is a highly relevant problem in video analysis. Applications can be found, for example, in dynamic medical or biological imaging, where the analysis and further processing of the dynamics of interest is often complicated by additional, unwanted dynamics, such as motion of the measurement subject. In this work, it is empirically shown that a representation of video data via untrained generator networks, together with a specific technique for latent space disentanglement that uses minimal, one-dimensional information on some of the underlying dynamics, allows to efficiently isolate different, highly non-linear motion types. In particular, such a representation allows to freeze any selection of motion types, and to obtain accurate independent representations of other dynamics of interest. Obtaining such a representation does not require any pre-training on a training data set, i.e., all parameters of the generator network are learned directly from a single video.
