Aljosa Osep, Paul Voigtlaender, Mark Weber, Jonathon Luiten, Bastian Leibe
TL;DR该研究提出了一种基于 4D Generic Video Tubes（4D-GVT）的方法，它利用运动线索、立体数据和目标实例分割可靠地提取已知和未知目标类型的时空对象建议，在未知类别的情况下，它表现出比其他方法更好的性能。
Abstract
Many high-level video understanding methods require input in the form of
object proposals. Currently, such proposals are predominantly generated with
the help of networks that were trained for detecting and segme