Location Prediction of Social Images via Generative Model

TL;DR

This paper introduces GTMI, a geographical topic model that integrates visual and textual content of social images to improve location prediction accuracy by modeling regional content distributions.

Contribution

The paper presents a novel geographical topic model that jointly learns from visual and textual data to enhance social image location prediction.

Findings

GTMI outperforms existing methods in location prediction accuracy.

Model effectively captures regional content distributions.

Joint modeling of text and visual features improves prediction results.

Abstract

The vast amount of geo-tagged social images has attracted great attention in research of predicting location using the plentiful content of images, such as visual content and textual description. Most of the existing researches use the text-based or vision-based method to predict location. There still exists a problem: how to effectively exploit the correlation between different types of content as well as their geographical distributions for location prediction. In this paper, we propose to predict image location by learning the latent relation between geographical location and multiple types of image content. In particularly, we propose a geographical topic model GTMI (geographical topic model of social image) to integrate multiple types of image content as well as the geographical distributions, In GTMI, image topic is modeled on both text vocabulary and visual feature. Each region has its own distribution over topics and hence has its own language model and vision pattern. The location of a new image is estimated based on the joint probability of image content and similarity measure on topic distribution between images. Experiment results demonstrate the performance of location prediction based on GTMI.