Recent advances in earth observation are opening up a new exciting area for exploration of satellite image data. In this session you will learn how to analyse this new data source with deep neural networks. Focusing on Emergency Response, you will learn (1) how to apply deep neural networks for Semantic Segmentation on satellite imagery. Additionally, we present recent advances of the Multimedia Satellite Task at MediaEval 2017 and show (2) how to extract and fuse content of natural disasters from Satellite Imagery and Social Media Streams. It is assumed that registrants are already familiar with fundamentals of deep neural networks.
Generative adversarial networks (GANs) have been applied for multiple cases, such as generating images and image completion. One interesting feature of GANs is the exploration in latent space, where new elements can appear caused by the interpolation between two seed elements. With this in mind, we're interested in exploring latent space in terms of adjective-noun pairs (ANP) able to capture subjectivity in visual content such as "cloudy sky" vs. "pretty sky." Although it is challenging for humans to find a smooth transition between two ANPs (similar to color gradient or color progression), the presented GANs are capable of generating such a gradient in the adjective domain and find new ANPs that lie in this (subjective) transition. As result, GANs offer a more quantified interpretation for this subjective progression and an explainability of the underlying latent space.
According to PricewaterhouseCooper's "Global Economic Crime Survey 2014", 37% of the 5,128 organizations surveyed had been victims of economic crime. Given this rise in economic crimes, investigators are working on novel forensic methods to detect financial fraud. Traditional data driven fraud detection methods are only capable of detecting transactions that correspond to already known fraud schemes. An open question is how to detect multi-dimensional patterns indicating 'anomalous' transactions in very large volumes of accounting data. This talk will present PricewaterhouseCooper's and the DFKI's recently developed approach to detect anomalous journal entries / transactions in large scale financial and accounting data by the use of deep learning and stacked autoencoders.