Video Segmentation via Multiple Granularity Analysis

Rui Yang, Bingbing Ni, Chao Ma, Yi Xu, Xiaokang Yang

CVPR 2017

doi:10.1109/CVPR.2017.676 /cvpr/2017/yang2017cvpr-video/

Abstract

We introduce a Multiple Granularity Analysis framework for video segmentation in a coarse-to-fine manner. We cast video segmentation as a spatio-temporal superpixel labeling problem. Benefited from the bounding volume provided by off-the-shelf object trackers, we estimate the foreground/ background super-pixel labeling using the spatiotemporal multiple instance learning algorithm to obtain coarse foreground/background separation within the volume. We further refine the segmentation mask in the pixel level using the graph-cut model. Extensive experiments on benchmark video datasets demonstrate the superior performance of the proposed video segmentation algorithm.

PDF CVPR Semantic Scholar

Cite

Text

Yang et al. "Video Segmentation via Multiple Granularity Analysis." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.676

Markdown

[Yang et al. "Video Segmentation via Multiple Granularity Analysis." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/yang2017cvpr-video/) doi:10.1109/CVPR.2017.676

BibTeX

@inproceedings{yang2017cvpr-video,
  title     = {{Video Segmentation via Multiple Granularity Analysis}},
  author    = {Yang, Rui and Ni, Bingbing and Ma, Chao and Xu, Yi and Yang, Xiaokang},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.676},
  url       = {https://mlanthology.org/cvpr/2017/yang2017cvpr-video/}
}