English

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

Computer Vision and Pattern Recognition 2021-02-02 v2

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.

Keywords

Cite

@article{arxiv.2008.00992,
  title  = {An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers},
  author = {Matteo Dunnhofer and Niki Martinel and Christian Micheloni},
  journal= {arXiv preprint arXiv:2008.00992},
  year   = {2021}
}

Comments

European Conference on Computer Vision (ECCV) 2020, Visual Object Tracking Challenge VOT2020 workshop

R2 v1 2026-06-23T17:36:28.681Z