Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?
This addresses the problem of automated human rights monitoring for organizations and activists, but it is incremental as it applies existing CNNs to a new dataset.
The paper tackles the problem of detecting human rights violations in images by introducing a new dataset (HRUN) and evaluating state-of-the-art CNN architectures, achieving up to 88.10% mean average precision.
After setting the performance benchmarks for image, video, speech and audio processing, deep convolutional networks have been core to the greatest advances in image recognition tasks in recent times. This raises the question of whether there are any benefit in targeting these remarkable deep architectures with the unattempted task of recognising human rights violations through digital images. Under this perspective, we introduce a new, well-sampled human rights-centric dataset called Human Rights Understanding (HRUN). We conduct a rigorous evaluation on a common ground by combining this dataset with different state-of-the-art deep convolutional architectures in order to achieve recognition of human rights violations. Experimental results on the HRUN dataset have shown that the best performing CNN architectures can achieve up to 88.10\% mean average precision. Additionally, our experiments demonstrate that increasing the size of the training samples is crucial for achieving an improvement on mean average precision principally when utilising very deep networks.