Paschalina Medentzidou

Machine Learning Engineer

About Me

Hi, my name is Paschalina Medentzidou and I am a machine learning engineer. I am currently working for the Information Technologies Institute. I enjoy extracting meaningful information from raw multimedia data and continuously learning new technologies on how to do that.

Working on security related projects I implement methods for object detection and motion based multiple object tracking using Deep Neural Networks. I get exposed to a series of machine learning frameworks (Caffe, Keras, Torch), programming languages (Python, Matlab, Lua), and technologies (MongoDB , Docker , Git Version Control). The fact that I am working on technologies that can make people’s lives better makes each day at work count for me!

Projects

Enriching 360 media with 3D storytelling and personalization elements

The end-goal of Hyper360 is to develop an enriched 360o media production toolset capable of delivering compelling personalized and interactive viewing experiences. This toolset will enable content distributors to deliver these media through broadband (OTT) to a variety of platforms. To this intend, existing work and technologies among the consortium members (360o video – DRK/FOKUS, personalization engine – FOKUS/CERTH, 3D capture – CERTH) will be adapted and extended by their respective IP owners while being evaluated for integration (ENG), with expertise in the fields of image processing (FOKUS/CERTH) and video quality analysis (JRS) utilized to design and create the required technological components to complete the proposed production solution, namely the 360o/3D fusion and emplacement technology (CERTH) and the online produced content quality analysis (JRS).

Virtual Reality Together

VR Together is a media project funded by the European Commission as part of the H2020 program, under the grant agreement 762111. It will last for 3 years (2017-2020) and operate with a budget of 3.9M€. We aim at radically improving the experience by innovating in how media formats are used (i.e., how audio, video and graphics are captured, delivered and rendered at users’ homes) demonstrating a significant improvement of the feeling of being there together and the photorealistic quality of the content.

Surveillance video archives investigation assistant

The SURVANT project aims to deliver an effective and efficient innovative system able to collect, analyse videos from heterogeneous repositories of surveillance videos and extract inter/intra-camera video analytics, supporting investigators in discovering suspicious criminal events within a huge amount of video tracks.

Large Scale Information Exploitation of Forensic Data

The LASIE project aims to design and implement an open and expandable framework that will significantly increase the efficiency of current investigation practices, by providing an automated initial analysis of the vast amounts of heterogeneous forensic data that analysts have to cope with. The framework will be able to handle forensic data that have been acquired from a variety of different sources including CCTV surveillance content, confiscated desktops and hard disks, mobile devices, Internet, social networks, handwritten and calligraphic documents.

ATLAS

Advanced Tourism Planning System

ATLAS seeks to create a step change in tourism services by advancing the state-of-the-art of the algorithms for fast geo‐aware social media tagging and annotation and geo‐aware multimedia information retrieval and recommendation. In particular, ATLAS aims at an innovative breakthrough in combining the just mentioned technologies for practical tourism services at a quality level that meets the expectations of the users.

Experience

Information Technologies Institute of CERTH

https://www.iti.gr/iti/index.html

Machine Learning Research Assistant

December 2019 - September 2020

CERTH/ITI is currently one of the leading Institutions of Greece and is conducting basic and applied research in established and emerging areas in the fields of Informatics, Telematics and Telecommunications. It is one of the largest IT research centers in Northern Greece with well-organized facilities, highly qualified personnel and a reputation as a top-level research IT institute in Greece and abroad, with long experience in numerous European and national Research and Development (R&D) projects.

Worked on EU Research Grant proposal preparation, EU project management, Market analysis

Information Technologies Institute of CERTH

https://www.iti.gr/iti/index.html

Machine Learning Research Assistant

July 2015 - January 2018

CERTH/ITI is currently one of the leading Institutions of Greece and is conducting basic and applied research in established and emerging areas in the fields of Informatics, Telematics and Telecommunications. It is one of the largest IT research centers in Northern Greece with well-organized facilities, highly qualified personnel and a reputation as a top-level research IT institute in Greece and abroad, with long experience in numerous European and national Research and Development (R&D) projects.

Worked on security related EU projects (LASIE-FP7,SURVANT-H2020) Implemented methods for real time object detection and motion based multiple object tracking using Deep Neural Networks applied on forensic multimedia data I used a series of machine learning frameworks (Caffe, Keras, Torch),Computer Vision library (OpenCV),programming languages (Python, Matlab, Lua), and technologies (MongoDB , Docker , Git VersionControl)

Artificial Intelligence & Information Analysis Lab, AUTh

http://www.aiia.csd.auth.gr/

Research Assistant / Software Developer

December 2014 - March 2015

AIIA Lab has been an active research group working for more than fifteen years in digital media and related areas. The group has strong cooperation with other Universities, research centers and industrial partners in the area of its interests through projects mainly funded by the European Union. AIIA LAb has undertaken around 35 international and 14 national research projects.

Worked on ATLAS project (Advanced Tourism Planning System) Proposed a novel technique to detect shot boundaries in videos and extract summaries automatically Collaborated constructively with other members of the team to accomplish integration of deliveredsystem, got familiar with working under pressure, presenting into technical meetings and writing deliverables

Education

Aristotle University of Thessaloniki

M.Sc. Informatics - Digital Media

2012-2014

School of Informatics, Department of Computer Science

The MSc of Informatics - Digital Media covers a range of advanced topics related to digital media including signal processing, computer vision, graphics, pattern recognition/machine learning and computational intelligence, including associated enabling technologies (e.g., language technologies, deep learning, computer animation, brain computer interfaces).

University of Macedonia

B.Sc. Applied Informatics

2006-2011

School of information sciences, Department of Applied Informatics

The degree of Applied Informatics includes advanced courses in Management Science, Economics, Finance, Business Administration, Quantitative Methods, as well as Computer and Internet Law. Emphasis is given on applications related to the analysis, design, development and management of systems for processing, storing, retrieving and transmitting information in the fields of Business Administration, Economics and Finance