We present an approach to semi-supervised video object segmentation, in the
context of the DAVIS 2017 challenge. Our approach combines category-based
object detection, category-independent object appearance segmentation and
temporal object tracking. We are motivated by the fact that the objects
semantic category tends not to change throughout the video while its appearance
and location can vary considerably. In order to capture the specific object
appearance independent of its category, for each video we train a fully
convolutional network using augmentations of the given annotated frame. We
refine the appearance segmentation mask with the bounding boxes provided either
by a semantic object detection network, when applicable, or by a previous frame
prediction. By introducing a temporal continuity constraint on the detected
boxes, we are able to improve the object segmentation mask of the appearance
network and achieve competitive results on the DAVIS datasets.

通过结合基于类别的目标检测、类别独立的目标外观分割和时间上的目标追踪等方法，通过训练全卷积网络对视频中的特定对象外观进行独立的分割，再引入对检测框时间上的连续性约束，从而实现半监督视频目标分割。