Occluded Video Instance Segmentation with Set Prediction Approach

ICCVW 2021 pp. 3843-3846

doi:10.1109/ICCVW54120.2021.00429 /iccvw/2021/bae2021iccvw-occluded/

Abstract

Occluded Video Instance Segmentation (OVIS) is a multi-task problem performing detection, segmentation, and tracking simultaneously under severe occlusions. We propose an extended model for the OVIS task based on the real-time one-stage instance segmentation method. The proposed model was applied to the OVIS dataset hold by the ICCV 2021 - Occluded Video Instance Segmentation Workshop 2021. We also show that the occlusions can be handled efficiently through one-stage approaches.

ICCVW Semantic Scholar

Cite

Text

Bae et al. "Occluded Video Instance Segmentation with Set Prediction Approach." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00429

Markdown

[Bae et al. "Occluded Video Instance Segmentation with Set Prediction Approach." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/bae2021iccvw-occluded/) doi:10.1109/ICCVW54120.2021.00429

BibTeX

@inproceedings{bae2021iccvw-occluded,
  title     = {{Occluded Video Instance Segmentation with Set Prediction Approach}},
  author    = {Bae, Heechul and Song, Soonyong and Park, Junhee},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {3843-3846},
  doi       = {10.1109/ICCVW54120.2021.00429},
  url       = {https://mlanthology.org/iccvw/2021/bae2021iccvw-occluded/}
}