Research Repository

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

Kalliatakis, Grigorios and Ehsan, Shoaib and Fasli, Maria and McDonald-Maier, Klaus D (2019) GET-AID: Visual Recognition of Human Rights Abuses via Global Emotional Traits. Working Paper. arxiv. (Unpublished)

[img]
Preview
Text
1902.03817v1.pdf

Download (4MB) | Preview

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.

Item Type: Monograph (Working Paper)
Additional Information: 10 pages, 6 figures
Uncontrolled Keywords: cs.CV, cs.CV
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 22 May 2020 15:46
Last Modified: 22 May 2020 16:15
URI: http://repository.essex.ac.uk/id/eprint/27587

Actions (login required)

View Item View Item