We propose to leverage a generic object tracker in order to perform object mining in large-scale unlabeled videos, captured in a realistic automotive setting. We present a dataset of more than 360'000 automatically mined object tracks from 10+ hours of video data (560'000 frames) and propose a method for automated novel category discovery and detector learning. In addition, we show preliminary results on using the mined tracks for object detector adaptation.
@article{arxiv.1809.07316,
title = {Towards Large-Scale Video Video Object Mining},
author = {Aljosa Osep and Paul Voigtlaender and Jonathon Luiten and Stefan Breuers and Bastian Leibe},
journal= {arXiv preprint arXiv:1809.07316},
year = {2018}
}
Comments
4 pages, 3 figures, 1 table. ECCV 2018 Workshop on Interactive and Adaptive Learning in an Open World