Joint temporal context exploitation and active learning for video segmentation

Yan Tian

doi:10.1016/j.patcog.2019.107158

Joint temporal context exploitation and active learning for video segmentation

2020-04-01

31

PRE

AI

DOI：10.1016/j.patcog.2019.107158

Original

Original request for help

Save

Abstract

En 中文

The segmentation of video, or separating out objects in the foreground, is an important application of pattern recognition and computer vision. Segmentation errors in pattern recognition approaches mainly come from difficulties in selecting maximally informative frames for learning. In this paper, we develop an approach to video segmentation that relies on temporal features by modeling the uncertainty of the distribution of different feature mask forms. We use those uncertainty values for unsupervised active learning. We evaluate our approach on the DAVIS16 annotated video data set and Shining3D dental video data set, and the results show our approach to be more accurate than other video segmentation approaches. (C) 2019 Elsevier Ltd. All rights reserved.

Keywords:

Video segmentation

Deep learning

Computer vision

Joint temporal context exploitation and active learning for video segmentation

Abstract

AI Summary

Journal

Organization