Our newest paper “An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers” is going to be presented on August 28th at the Visual Object Tracking Challenge VOT2020 workshop, held in conjunction with the European Conference on Computer Vision (ECCV) 2020. In this work, we propose an analysis of the most recent segmentation methods that are conditioned on a particular object, in order to transform any bounding-box tracker into a segmentation tracker.
Here is the 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.
and in the following you can have a look to a teaser video of our study (follow the links in the description for the arXiv preprint, a longer presentation, and qualitative examples).