English

Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps

Computer Vision and Pattern Recognition 2021-04-22 v1

Abstract

We propose a novel guided interactive segmentation (GIS) algorithm for video objects to improve the segmentation accuracy and reduce the interaction time. First, we design the reliability-based attention module to analyze the reliability of multiple annotated frames. Second, we develop the intersection-aware propagation module to propagate segmentation results to neighboring frames. Third, we introduce the GIS mechanism for a user to select unsatisfactory frames quickly with less effort. Experimental results demonstrate that the proposed algorithm provides more accurate segmentation results at a faster speed than conventional algorithms. Codes are available at https://github.com/yuk6heo/GIS-RAmap.

Keywords

Cite

@article{arxiv.2104.10386,
  title  = {Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps},
  author = {Yuk Heo and Yeong Jun Koh and Chang-Su Kim},
  journal= {arXiv preprint arXiv:2104.10386},
  year   = {2021}
}

Comments

accepted to CVPR2021 (oral)

R2 v1 2026-06-24T01:23:31.984Z