# GET-AID: Visual Recognition of Human Rights Abuses via Global Emotional Traits

## TL;DR

GET-AID is a novel visual recognition system that detects human rights abuses by analyzing emotional traits in images, significantly improving detection coverage over previous methods.

## Contribution

The paper introduces GET-AID, a new model that predicts global emotional traits to identify human rights violations in images, combining emotional analysis with CNN classification.

## Key findings

- Improves detection coverage by up to 23.73% for child labour.
- Achieves up to 57.21% improvement for displaced populations.
- Demonstrates effectiveness on the Human Rights Archive dataset.

## Abstract

In the era of social media and big data, the use of visual evidence to document conflict and human rights abuse has become an important element for human rights organizations and advocates. In this paper, we address the task of detecting two types of human rights abuses in challenging, everyday photos: (1) child labour, and (2) displaced populations. We propose a novel model that is driven by a human-centric approach. Our hypothesis is that the emotional state of a person -- how positive or pleasant an emotion is, and the control level of the situation by the person -- are powerful cues for perceiving potential human rights violations. To exploit these cues, our model learns to predict global emotional traits over a given image based on the joint analysis of every detected person and the whole scene. By integrating these predictions with a data-driven convolutional neural network (CNN) classifier, our system efficiently infers potential human rights abuses in a clean, end-to-end system we call GET-AID (from Global Emotional Traits for Abuse IDentification). Extensive experiments are performed to verify our method on the recently introduced subset of Human Rights Archive (HRA) dataset (2 violation categories with the same number of positive and negative samples), where we show quantitatively compelling results. Compared with previous works and the sole use of a CNN classifier, this paper improves the coverage up to 23.73% for child labour and 57.21% for displaced populations. Our dataset, codes and trained models are available online at https://github.com/GKalliatakis/GET-AID.