Unsupervised Object Segmentation in Video by Efficient Selection of Highly Probable Positive Features

Abstract

We address an essential problem in computer vision, that of unsupervised foreground object segmentation in video, where a main object of interest in a video sequence should be automatically separated from its background. An efficient solution to this task would enable large-scale video interpretation at a high semantic level in the absence of the costly… (More)
DOI: 10.1109/ICCV.2017.544

10 Figures and Tables

Topics

  • Presentations referencing similar topics