We propose to implicitly learn to extract geo-temporal image features, which are mid-level features related to when and where an image was captured, by explicitly optimizing for a set of location and time estimation tasks. To train our method, we take advantage of a large image dataset, captured by outdoor webcams and cell phones. The only form of supervision we provide are the known capture time and location of each image. We find that our approach learns features that are related to natural appearance changes in outdoor scenes. Additionally, we demonstrate the application of these geo-temporal features to time and location estimation.
@article{arxiv.1909.07499,
title = {Learning Geo-Temporal Image Features},
author = {Menghua Zhai and Tawfiq Salem and Connor Greenwell and Scott Workman and Robert Pless and Nathan Jacobs},
journal= {arXiv preprint arXiv:1909.07499},
year = {2019}
}