Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu...
TL;DR本文提出了一种基于视频对象重识别的视频分割方法,通过使用自适应的目标重识别机制来避免传统方法中的漂移问题和无法处理大位移的弊端,该方法在 2017 年 DAVIS Challenge 中取得了最佳性能。
Abstract
Conventional video segmentation methods often rely on temporal continuity to
propagate masks. Such an assumption suffers from issues like drifting and
inability to handle large displacement. To overcome these issues, we formulate
an effective mechanism to prevent the target from being