Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
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.
Cite
Text
Heo et al. "Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00724Markdown
[Heo et al. "Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/heo2021cvpr-guided/) doi:10.1109/CVPR46437.2021.00724BibTeX
@inproceedings{heo2021cvpr-guided,
title = {{Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps}},
author = {Heo, Yuk and Koh, Yeong Jun and Kim, Chang-Su},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2021},
pages = {7322-7330},
doi = {10.1109/CVPR46437.2021.00724},
url = {https://mlanthology.org/cvpr/2021/heo2021cvpr-guided/}
}