CityGuessr: City-Level Video Geo-Localization on a Global Scale

TL;DR

This paper introduces CityGuessr, a new large-scale dataset and a transformer-based model for global video geolocalization, predicting city, state, country, and continent from videos.

Contribution

It presents the first comprehensive approach for worldwide video geolocalization, including a new dataset and a novel transformer architecture with scene and text label integration.

Findings

Achieved state-of-the-art performance on CityGuessr68k and Mapillary datasets.

Demonstrated the effectiveness of self-cross attention and text label alignment.

Provided a new benchmark for global video geolocalization.

Abstract

Video geolocalization is a crucial problem in current times. Given just a video, ascertaining where it was captured from can have a plethora of advantages. The problem of worldwide geolocalization has been tackled before, but only using the image modality. Its video counterpart remains relatively unexplored. Meanwhile, video geolocalization has also garnered some attention in the recent past, but the existing methods are all restricted to specific regions. This motivates us to explore the problem of video geolocalization at a global scale. Hence, we propose a novel problem of worldwide video geolocalization with the objective of hierarchically predicting the correct city, state/province, country, and continent, given a video. However, no large scale video datasets that have extensive worldwide coverage exist, to train models for solving this problem. To this end, we introduce a new dataset, CityGuessr68k comprising of 68,269 videos from 166 cities all over the world. We also propose a novel baseline approach to this problem, by designing a transformer-based architecture comprising of an elegant Self-Cross Attention module for incorporating scenes as well as a TextLabel Alignment strategy for distilling knowledge from textlabels in feature space. To further enhance our location prediction, we also utilize soft-scene labels. Finally we demonstrate the performance of our method on our new dataset as well as Mapillary(MSLS). Our code and datasets are available at: https://github.com/ParthPK/CityGuessr