Location Prediction of Social Images via Generative Model
This work addresses the challenge of effectively exploiting correlations between different content types for location prediction in social images, representing an incremental improvement over existing text-based or vision-based methods.
The paper tackled the problem of predicting the geographical location of social images by integrating multiple content types and their geographical distributions, proposing a geographical topic model (GTMI) that models image topics on both text and visual features, and demonstrated its performance in location prediction experiments.
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.