Early and Late Fusion of Classifiers for the MediaEval 2018 Medico Task

AAU/ITEC researchers Mario Taschwer, Klaus Schöffmann, and Jürgen Primus collaborated with Oge Marques (FAU, USA) on a research challenge targeting automatic classification of endoscopic images of the human gastro-intestinal tract. The challenge was posed as the MediaEval 2018 Medico task and called not only for classification effectiveness, but also for run-time efficiency of proposed approaches. The joint AAU-FAU team therefore proposed a combination of CNN-based feature extraction with traditional machine learning algorithms and achieved respectable results in comparison to deep-learning based approaches submitted by other participants, which has been honored with a “distinctive mention” by Medico task organizers. The AAU-FAU approach has been presented remotely by Mario Taschwer at the MediaEval 2018 Workshop, Sophia Antipolis, France, on October 30, 2018.

Paper and slides are available here.

Klaus Schöffmann, Bernd Münzer & Sabrina Kletz @ ACM International Conference on Multimedia in Seoul, South Korea


From October 22-26, 2018, Klaus Schöffmann and people from his group (Sabrina Kletz and Bernd Münzer) participated in the ACM International Conference on Multimedia in Seoul, South Korea. Klaus Schöffmann presented two well-attended tutorials – one on “Interactive Video Search“ together with colleagues from Prague University, JOANNEUM RESEARCH, and NIST – and another one on “Medical Multimedia” together with Bernd Münzer and colleagues from Simula Research (the slides for both tutorials can be found below). Moreover, Sabrina Kletz successfully presented her PhD work there in the Doctoral Consortium and received some feedback from the community.

Read more

Philipp Moll

Philipp Moll presented his paper on “Wireless Network Emulation for Research on Information Centric Networking” at the ACM WiNTECH Workshop 2018.

The WiNTECH workshop explicitly deals with methodological and technical issues that have to be faced for defining, running, controlling and benchmarking experiments on wireless solutions. The workshop, that this year reach the 12th edition, has a consolidated tradition for bringing together an important number of researchers and industry players working in different aspects of experimental wireless communications. This year the workshop was held in conjunction with the International Conference on Mobile Computing and Networking (MobiCom) in New Delhi, India. Read more

Prof. Radu Prodan

Prof. Radu Prodan @ India

, ,

From October 13-22, 2018 Prof. Radu Prodan visited Chandigarh University and Lovely Professional University in India for interaction with research scholars and discussions about the common research projects.


ITEC researchers presenting at 25th IEEE International Conference on Image Processing (ICIP) in Athens, Greece on October 7-10, 2018


The 25th IEEE International Conference on Image Processing (ICIP; https://2018.ieeeicip.org/) will be held in Athens, Greece on October 7-10, 2018. ITEC researcher Anatoliy Zabrovskiy will present “A Practical Evaluation of Video Codecs for Large-Scale HTTP Adaptive Streaming Services” within the special session on “Video Coding at Scale”. The abstract is as follows: The number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audiovisual content accounts for the majority of today’s internet traffic. Although the internet bandwidth increases also constantly, audio-visual compression technology is inevitable and we are currently facing the challenge to be confronted with multiple video codecs. This paper provides a practical evaluation of state of the art video codecs (i. e., AV1, AVC/libx264, HEVC/libx265, VP9/Iibvpx-vp9) for large-scale HTTP adaptive streaming services. In anticipation of the results, AV1 shows promising performance compared to established video codecs. Additionally, AV1 is intended to be royalty free making it worthwhile to be considered for large scale HTTP adaptive streaming services. Read more

Prof. Radu Prodan (Principal Investigator, ARTICONF, European Union’s Horizon 2020 research and innovation H2020-ICT-2018-2) sharing insights about next generation social media

, , , ,

Please find the full AAU news blog article here.

Klaus Schöffmann and Mario Taschwer outline the research goals of their new FWF stand-alone project on relevance detection in ophthalmic surgery videos.

, ,

The OVID research project (relevance detection in Ophthalmic surgery VIDeos), funded by the Austrian Science Fund (FWF), will start on October 1st, 2018 and run for three years. Together with research partners from Klinikum Klagenfurt, it will allow three PhD students (and an accompanying student assistant) to investigate challenging new research questions at the intersection of computer science and ophthalmic surgery. In particular, automatic classification and prediction of relevant content in video recordings from ophthalmic surgeries (e.g., operation phases, surgical actions, irregular events and their cause) should be evaluated for the purpose of medical training and retrospective analysis of irregularities. The researchers want to address these goals by using methods from video analysis, video compression, and machine learning (including deep neural networks). An interview summarizing the research goals can be found here (in German): https://www.aau.at/blog/relevante-stellen-in-augenoperationsvideos-maschinell-erkennen/

Hermann Hellwagner @ IKT-Konvent 2018


Hermann Hellwagner actively participated in the “IKT-Konvent 2018” in Vienna on September 17, 2018. The event was to boost Austrian R&D, commercial, and educational activities toward the fully digital and connected world. As one of the panel members, Hellwagner contributed to the session “5G Applications” which discussed potential applications and benefits of future 5G networks, how to prototype and introduce 5G infrastructure and applications, and which cooperations among industry, academia, and government are required to perform 5G projects and become a frontrunner in the 5G area.

Christian Timmerer

Christian Timmerer on the PhD defense committee of Mario Cordina and gives an invited talk about “HTTP Adaptive Streaming — State of the Art and Challenges Ahead”


On September 18, 2018 Christian Timmerer participates on the PhD defense committee of Mario Cordina at the University of Malta. The title of Mario Cordina’s PhD is “Cross-Layer Design for Multi-View Video Plus Depth Transmission over LTE Networks in Crowd Event Scenarios”. Additionally, he delivered an invited talk about “HTTP Adaptive Streaming — State of the Art and Challenges Ahead” at the University of Malta, Department of Communications and Computer Engineering.

Mathias Lux

Talk on Indexing of Large Data Sets in Image Retrieval at Simula Metropolitan, Oslo, NO


Mathias Lux was invited to give a talk at Simula Metropolitan, a joint research center of SIMULA research labs and Oslo Metropolitan University. Besides the talk he took the opportunity to work for two days with the people at SIMULA and talk about future and ongoing projects. Read more