Political Posters Identification with Appearance-Text Fusion

TL;DR

This paper introduces a novel appearance-text fusion method for accurately identifying political posters, supported by a new dataset and comprehensive analysis of patterns and outliers.

Contribution

The work presents the first curated dataset of 13K political images and a fusion model that significantly improves classification accuracy of political posters.

Findings

Created a dataset of 13,000 political images including 3,000 posters

Analyzed common patterns and outliers in political posters

Achieved high accuracy in classifying political posters using appearance-text fusion

Abstract

In this paper, we propose a method that efficiently utilizes appearance features and text vectors to accurately classify political posters from other similar political images. The majority of this work focuses on political posters that are designed to serve as a promotion of a certain political event, and the automated identification of which can lead to the generation of detailed statistics and meets the judgment needs in a variety of areas. Starting with a comprehensive keyword list for politicians and political events, we curate for the first time an effective and practical political poster dataset containing 13K human-labeled political images, including 3K political posters that explicitly support a movement or a campaign. Second, we make a thorough case study for this dataset and analyze common patterns and outliers of political posters. Finally, we propose a model that combines the power of both appearance and text information to classify political posters with significantly high accuracy.