KMi Publications

Tech Reports

Tech Report kmi-08-03 Abstract


Modelling social context to improve online multimedia search
Techreport ID: kmi-08-03
Date: 2008
Author(s): Adam Rae
Download PDF

As the cost of production, storage and dissemination has plummeted for images, audio and video, challenges have arisen regarding how to most e?ectively handle this wealth of information. Digital recording devices have become cheaper, more widely available and are able to recording in better quality than ever before. Media representation has given us lossy and lossless file formats suitable for many different situations, from satellite broadcast to mobile streaming, each with their unique requirements and capabilities. Digital file storage devices have grown more capacious, high performing and more reliable. The one area that has not caught up is how to search and retrieval multimedia efficiently and e?ectively in these new, vast data sets and this is the focus for my work. More specifically, I wish to investigate the relationship between social context data and its e?ect on multimedia information retrieval.

Publication(s):

Probation review report carried out around 9 months after the start of doctoral work. Submitted 28/08/08
 
KMi Publications
 

Multimedia and Information Systems is...


Multimedia and Information Systems
Our research is centred around the theme of Multimedia Information Retrieval, ie, Video Search Engines, Image Databases, Spoken Document Retrieval, Music Retrieval, Query Languages and Query Mediation.

We focus on content-based information retrieval over a wide range of data spanning form unstructured text and unlabelled images over spoken documents and music to videos. This encompasses the modelling of human perception of relevance and similarity, the learning from user actions and the up-to-date presentation of information. Currently we are building a research version of an integrated multimedia information retrieval system MIR to be used as a research prototype. We aim for a system that understands the user's information need and successfully links it to the appropriate information sources, be it a report or a TV news clip. This work is guided by the vision that an automated knowledge extraction system ultimately empowers people making efficient use of information sources without the burden of filing data into specialised databases.

Visit the MMIS website