Aristotle University Of Thessaloniki (AUTH)
Multimedia big data analysis and retrieval
Abstract
dc:descriptionIn this thesis, the problem of analyzing and retrieving content from multimedia big data datasets and especially the computationally efficient approaches for handling, analysing and retrieving multimedia descriptors, is studied. Initially, a presentation and analysis of related work, with emphasis on multimedia, the Internet and the social web, is conducted. Next, a semi-supervised clustering method for large datasets of high-dimensional descriptor vectors is presented along with a comparative evaluation with other state of the art methods. The presentation of a social event detection method, from social multimedia content, follows. Moreover, a methodology for analysing high-dimensional multimedia vectors is presented and evaluated for the computationally efficient indexing of such vectors. In parallel, the thesis presents a methodology and the research findings of real-time analysis and retrieval of high volumes of multimedia content with the synergy of the crowd in a hybrid human machine retrieval approach. Finally, the thesis presents a protocol for efficient distributed searching for multimedia content within content centric networks as well as the application of the protocol and methodology in images and 3D content. This thesis is concluded with the short presentation of the software tools that were implemented during these studies.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2017
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Semertzidis, Theodoros
- Σεμερτζίδης, Θεόδωρος
Subjects
dc:subject × 16- Αναζήτηση πολυμέσων
- Μεγάλα πολυμεσικά δεδομένα
- Ανάλυση μεγάλων δεδομένων
- Δεδομένα κοινωνικών μέσων
- Multimedia retrieval
- Multimedia big data
- Big data analysis
- Social media data
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Natural Sciences
- Computer and Information Sciences
- Engineering and Technology
- Electrical Engineering, Electronic Engineering, Information Engineering
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/41980