KMi Seminars
Semantic Multimedia Information: Mining, Fusion and Extraction
This event took place on Wednesday 14 February 2007 at 12:00

 
Joćo Magalhćes Imperial College London, and KMi, The Open University

The extraction of semantic information from multimedia content is a research area that faces multiple challenges: scalability; data scarcity; multiple statistical models for each modality; computational limitations when processing large-scale training datasets; incorrect ground truth...

To address some of the issues hindering multimedia retrieval applications we propose a novel learning framework to extract semantic multimedia information. The framework combines both knowledge and statistical data, and it is divided in three parts: (1) multimedia mining, (2) multi-modal information fusion, and (3) semantic information extraction.

We will discuss several aspects of the framework, such as, scalability, its solid statistical foundation (borrowed from Generalized Linear Models and Bayesian Theory), how it is able to elegantly cope with different modalities, and its performance on semantic image retrieval and large-scale semantic video retrieval.

 
KMi Seminars Event | SSSW 2013, The 10th Summer School on Ontology Engineering and the Semantic Web Journal | 25 years of knowledge acquisition
 

Narrative Hypermedia is...


Narrative Hypermedia
Narrative is concerned fundamentally with coherence, for instance, whether that be a fiction, an historical account or an argument, none of which 'make sense' unless they are put together in a coherent manner.

Hypermedia is the combination of hypertext for linking and structuring multimedia information.

Narrative Hypermedia is therefore concerned with how all of the above narrative forms, plus the many other diverse forms of discourse possible on the Web, can be effectively designed to communicate coherent conceptual structures, drawing inspiration from theories in narratology, semiotics, psycholinguistics and film.