Christian Koch

Moritz Lode, Michael Örtl, Christian Koch et al.

This work discusses and implements the application of speaker recognition for the detection of collaborations in YouTube videos. CATANA, an existing framework for detection and analysis of YouTube collaborations, is utilizing face recognition for the detection of collaborators, which naturally performs poor on video-content without appearing faces. This work proposes an extension of CATANA using active speaker detection and speaker recognition to improve the detection accuracy.

Christian Koch, Moritz Lode, Denny Stohr et al.

YouTube is one of the most popular platforms for streaming of user-generated video. Nowadays, professional YouTubers are organized in so called multi-channel networks (MCNs). These networks offer services such as brand deals, equipment, and strategic advice in exchange for a share of the YouTubers' revenue. A major strategy to gain more subscribers and, hence, revenue is collaborating with other YouTubers. Yet, collaborations on YouTube have not been studied in a detailed quantitative manner. This paper aims to close this gap with the following contributions. First, we collect a YouTube dataset covering video statistics over three months for 7,942 channels. Second, we design a framework for collaboration detection given a previously unknown number of persons featuring in YouTube videos. We denote this framework for the analysis of collaborations in YouTube videos using a Deep Neural Network (DNN) based approach as CATANA. Third, we analyze about 2.4 years of video content and use CATANA to answer research questions providing guidance for YouTubers and MCNs for efficient collaboration strategies. Thereby, we focus on (i) collaboration frequency and partner selectivity, (ii) the influence of MCNs on channel collaborations, (iii) collaborating channel types, and (iv) the impact of collaborations on video and channel popularity. Our results show that collaborations are in many cases significantly beneficial in terms of viewers and newly attracted subscribers for both collaborating channels, showing often more than 100% popularity growth compared with non-collaboration videos.

Henning Puttnies, Peter Danielis, Christian Koch et al.

On the one side, network simulation frameworks are important tools for research and development activities to evaluate novel approaches in a time- and cost-efficient way. On the other side, Java as a highly platform-independent programming language is ideally suited for rapid prototyping in heterogeneous scenarios. Consequently, Java simulation frameworks could be used to firstly perform functional verification of new approaches (and protocols) in a simulation environment and afterwards, to evaluate these approaches in real testbeds using prototype Java implementations. Finally, the simulation models can be refined using real world measurement data. Unfortunately, there is to the best of our knowledge no satisfying Java framework for network simulation, as the OMNeT++ Java support ended with OMNeT++ version 4.6. Hence, our contributions are as follows: we present Java extensions for OMNeT++ 5.0 that enable the execution of Java simulation models and give a detailed explanation of the working principles of the OMNeT++ Java extensions that are based on Java Native Interface. We conduct several case studies to evaluate the concept of Java extensions for OMNeT++. Most importantly, we show that the combined use of Java simulation models and C++ models (e.g., from the INET framework) is possible.