An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers

Matteo Dunnhofer, Niki Martinel, Christian Micheloni

ECCVW 2020 pp. 618-636

doi:10.1007/978-3-030-68238-5_41 /eccvw/2020/dunnhofer2020eccvw-exploration/

Abstract

Visual object tracking is the problem of predicting a target object's state in a video. Generally, bounding-boxes have been used to represent states, and a surge of effort has been spent by the community to produce efficient causal algorithms capable of locating targets with such representations. As the field is moving towards binary segmentation masks to define objects more precisely, in this paper we propose to extensively explore target-conditioned segmentation methods available in the computer vision community, in order to transform any bounding-box tracker into a segmentation tracker. Our analysis shows that such methods allow trackers to compete with recently proposed segmentation trackers, while performing quasi real-time.

PDF ECCVW Semantic Scholar

Cite

Text

Dunnhofer et al. "An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-68238-5_41

Markdown

[Dunnhofer et al. "An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/dunnhofer2020eccvw-exploration/) doi:10.1007/978-3-030-68238-5_41

BibTeX

@inproceedings{dunnhofer2020eccvw-exploration,
  title     = {{An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers}},
  author    = {Dunnhofer, Matteo and Martinel, Niki and Micheloni, Christian},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {618-636},
  doi       = {10.1007/978-3-030-68238-5_41},
  url       = {https://mlanthology.org/eccvw/2020/dunnhofer2020eccvw-exploration/}
}