Harald Kosch

Maximilian Schiedermeier, Omar Hasan, Tobias Mayer et al.

High voter turnout in elections and referendums is very desirable in order to ensure a robust democracy. Secure electronic voting is a vision for the future of elections and referendums. Such a system can counteract factors that hinder strong voter turnout such as the requirement of physical presence during limited hours at polling stations. However, this vision brings transparency and confidentiality requirements that render the design of such solutions challenging. Specifically, the counting must be implemented in a reproducible way and the ballots of individual voters must remain concealed. In this paper, we propose and evaluate a referendum protocol that ensures transparency, confidentiality, and integrity, in trustless networks. The protocol is built by combining Secure Multi-Party Computation (SMPC) and Distributed Ledger or Blockchain technology. The persistence and immutability of the protocol communication allows verifiability of the referendum outcome on the client side. Voters therefore do not need to trust in third parties. We provide a formal description and conduct a thorough security evaluation of our proposal.

Benjamin Planche, Xuejian Rong, Ziyan Wu et al.

We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be hallucinated locally in consistence with previous observations, hallucinations and global priors, and (d) hallucinations are statistical in nature, i.e., different scenes can be generated from the same observations. To achieve this, we model the virtual scene, where an active agent at each step can either perceive an observed part of the scene or generate a local hallucination. The latter can be interpreted as the agent's expectation at this step through the scene and can be applied to autonomous navigation. In the limit of observing real data at each point, our method converges to solving the SLAM problem. It can otherwise sample entirely imagined scenes from prior distributions. Besides autonomous agents, applications include problems where large data is required for building robust real-world applications, but few samples are available. We demonstrate efficacy on various 2D as well as 3D data.

Benjamin Planche, Sergey Zakharov, Ziyan Wu et al.

While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic samples along domain adaptation schemes to prepare algorithms for the target domain. Tackling this problem from a different angle, we introduce a pipeline to map unseen target samples into the synthetic domain used to train task-specific methods. Denoising the data and retaining only the features these recognition algorithms are familiar with, our solution greatly improves their performance. As this mapping is easier to learn than the opposite one (ie to learn to generate realistic features to augment the source samples), we demonstrate how our whole solution can be trained purely on augmented synthetic data, and still perform better than methods trained with domain-relevant information (eg real images or realistic textures for the 3D models). Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images.

Sergey Zakharov, Benjamin Planche, Ziyan Wu et al.

With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images. However, discrepancies with the real data acquired from various depth sensors still noticeably impede progress. Previous works adopted unsupervised approaches to generate more realistic depth data, but they all require real scans for training, even if unlabeled. This still represents a strong requirement, especially when considering real-life/industrial settings where real training images are hard or impossible to acquire, but texture-less 3D models are available. We thus propose a novel approach leveraging only CAD models to bridge the realism gap. Purely trained on synthetic data, playing against an extensive augmentation pipeline in an unsupervised manner, our generative adversarial network learns to effectively segment depth images and recover the clean synthetic-looking depth information even from partial occlusions. As our solution is not only fully decoupled from the real domains but also from the task-specific analytics, the pre-processed scans can be handed to any kind and number of recognition methods also trained on synthetic data. Through various experiments, we demonstrate how this simplifies their training and consistently enhances their performance, with results on par with the same methods trained on real data, and better than usual approaches doing the reverse mapping.

Benjamin Planche, Ziyan Wu, Kai Ma et al.

Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data. Collecting such datasets is however a tedious, often impossible task; hence a surge in approaches relying solely on synthetic data for their training. For depth images however, discrepancies with real scans still noticeably affect the end performance. We thus propose an end-to-end framework which simulates the whole mechanism of these devices, generating realistic depth data from 3D models by comprehensively modeling vital factors e.g. sensor noise, material reflectance, surface geometry. Not only does our solution cover a wider range of sensors and achieve more realistic results than previous methods, assessed through extended evaluation, but we go further by measuring the impact on the training of neural networks for various recognition tasks; demonstrating how our pipeline seamlessly integrates such architectures and consistently enhances their performance.

Mazen Alsarem, Pierre-Edouard Portier, Sylvie Calabretto et al.

The advances of the Linked Open Data (LOD) initiative are giving rise to a more structured web of data. Indeed, a few datasets act as hubs (e.g., DBpedia) connecting many other datasets. They also made possible new web services for entity detection inside plain text (e.g., DBpedia Spotlight), thus allowing for new applications that will benefit from a combination of the web of documents and the web of data. To ease the emergence of these new use-cases, we propose a query-biased algorithm for the ranking of entities detected inside a web page. Our algorithm combine link analysis with dimensionality reduction. We use crowdsourcing for building a publicly available and reusable dataset on which we compare our algorithm to the state of the art. Finally, we use this algorithm for the construction of semantic snippets for which we evaluate the usability and the usefulness with a crowdsourcing-based approach.

Mazen Alsarem, Pierre-Edouard Portier, Sylvie Calabretto et al.

The advances of the Linked Open Data (LOD) initiative are giving rise to a more structured Web of data. Indeed, a few datasets act as hubs (e.g., DBpedia) connecting many other datasets. They also made possible new Web services for entity detection inside plain text (e.g., DBpedia Spotlight), thus allowing for new applications that can benefit from a combination of the Web of documents and the Web of data. To ease the emergence of these new applications, we propose a query-biased algorithm (LDRANK) for the ranking of web of data resources with associated textual data. Our algorithm combines link analysis with dimensionality reduction. We use crowdsourcing for building a publicly available and reusable dataset for the evaluation of query-biased ranking of Web of data resources detected in Web pages. We show that, on this dataset, LDRANK outperforms the state of the art. Finally, we use this algorithm for the construction of semantic snippets of which we evaluate the usefulness with a crowdsourcing-based approach.