K
Katerina Andreadou
Researcher at Information Technology Institute
Publications - 4
Citations - 107
Katerina Andreadou is an academic researcher from Information Technology Institute. The author has contributed to research in topics: External Data Representation & Feature detection (computer vision). The author has an hindex of 3, co-authored 4 publications receiving 72 citations.
Papers
More filters
Verifying Multimedia Use at MediaEval 2015
Christina Boididou,Katerina Andreadou,Symeon Papadopoulos,Duc-Tien Dang-Nguyen,Giulia Boato,Michael Riegler,Yiannis Kompatsiaris +6 more
TL;DR: An overview of the Verifying Multimedia Use task, which deals with the automatic detection of manipulation and misuse of Web multimedia content, and a large corpus of real-world cases of images that were distributed through tweets, along with manually assigned labels regarding their use.
Book ChapterDOI
A Unified Model for Socially Interconnected Multimedia-Enriched Objects
Theodora Tsikrika,Katerina Andreadou,Anastasia Moumtzidou,Emmanouil Schinas,Symeon Papadopoulos,Stefanos Vrochidis,Ioannis Kompatsiaris +6 more
TL;DR: A flexible model for describing Socially Interconnected MultiMedia-enriched Objects (SIMMO) that integrates in a unified manner the representation of multimedia and social features in online environments and ensures interoperability is proposed.
Book ChapterDOI
Media REVEALr: A Social Multimedia Monitoring and Intelligence System for Web Multimedia Verification
Katerina Andreadou,Symeon Papadopoulos,Lazaros Apostolidis,Anastasia Krithara,Yiannis Kompatsiaris +4 more
TL;DR: Media REVEALr is proposed, a scalable and efficient content-based media crawling and indexing framework featuring a novel and resilient near-duplicate detection approach and intelligent content- and context-based aggregation capabilities (e.g. clustering, named entity extraction).
Proceedings ArticleDOI
Web image size prediction for efficient focused image crawling
TL;DR: This paper explores the challenge of predicting the size of images on the Web based only on their URL and information extracted from the surrounding HTML code, and presents two different methodologies based on a common text classification approach using the n-grams or tokens of the image URLs and the second one relies on the HTML elements surrounding the image.