Spatio-temporal convolution kernels

Spatio-temporal convolution kernels
复制标题

DOI:
10.1007/s10994-015-5520-1
复制
发表时间:
2016-02-01
期刊:
影响因子:
7.5
通讯作者:
Brefeld, Ulf
Brefeld, Ulf
中科院分区:
计算机科学3区
文献类型:
--
作者:
Knauf, Konstantin;Memmert, Daniel;Brefeld, Ulf

文献摘要

被引文献

相似文献

在许多不同的领域和应用中记录同时运动的物体的轨迹数据。然而,利用这些数据的现有技术往往无法捕捉特征或缺乏理论保证。我们提出了一类新的时空卷积核来捕获多对象场景中的相似性。抽象内核是时间内核和空间内核的组合,其实际实例化取决于手头的应用程序。从经验上讲,我们比较我们的内核和有效的近似基线技术聚类任务,使用人工和真实的世界的数据,从团队运动。
Trajectory data of simultaneously moving objects is being recorded in many different domains and applications. However, existing techniques that utilise such data often fail to capture characteristic traits or lack theoretical guarantees. We propose a novel class of spatio-temporal convolution kernels to capture similarities in multi-object scenarios. The abstract kernel is a composition of a temporal and a spatial kernel and its actual instantiations depend on the application at hand. Empirically, we compare our kernels and efficient approximations thereof to baseline techniques for clustering tasks using artificial and real world data from team sports.