Second Workshop on the Many Faces of Multimedia Semantics

Description

Information is increasingly becoming ubiquitous and all-pervasive, with the World-Wide Web as its primary repository. The rapid growth of information on the Web creates new challenges for information retrieval. Recently, there has been a growing interest in the investigation and development of the next generation web – the Semantic Web. The Semantic Web enables programs/agents to automatically understand what data is about, and therefore, bridge the, so-called, semantic gap between the ways in which users request web resources and the real needs of those users, ultimately improving the quality of web information retrieval.

Multimedia information has always been part of the Semantic Web paradigm, but, in general, has been discussed very simplistically by the Semantic Web community. We believe that, rather than trying to discover a media object’s hidden meaning, one should formulate ways of managing media objects so as to help people make more intelligent use of them. The relationship between users and media objects should be studied. Media objects should be interpreted relative to the particular goal or point-of-view of a particular user at a particular time.

Content-based descriptors are necessary to this process. Major search engines are in the process of rolling out A/V search capabilities. At the same time, such descriptions are definitely not sufficient. Context is also important, and should be managed. The area of emergent multimedia semantics has been initiated to study the measured interactions between users and media object, with the ultimate goal of trying to satisfy the user community by providing them with the media objects they require, based on their individual previous media interactions.

The arrival of Web 2.0 has added new paradigms to the media mix. Such concepts as a folksonomy, a form of emergent semantics, introduces a collaborative, dynamic approach to the generation of ontologies and media object semantics. That such an approach results in a stable semantics, though surprising, has been recently demonstrated.

List of Topics

We welcome all papers relevant to topics in multimedia semantics, including those at the confluence of multimedia information management, the Semantic Web, and Web 2.0, such as,

- Multimedia ontologies
- Approaches using metadata standards such as MPEG7
- Computational semiotics
- Conceptual clustering
- Emergent semantics
- Event representation and detection
- Folksonomies
- Genre detection
- Industrial use-cases and applications
- Intelligent browsing and visualization
- Media ontology learning
- Media web mining
- Modeling and recognition of visual objects and actions
- Multimedia extraction and annotation
- Multimedia ontologies
- Multisensory data integration and fusion for decision making
- Perception and cognition
- Semantic metadata for mobile applications
- Semantics enabled multimedia applications (including search, browsing, retrieval, visualization)
- Semantics enabled networks and middleware for multimedia applications
- Semantics based search and integration of multimedia and digital content
- Semi automatic and automatic methods for multimedia annotation
- Social networking
- Spectral methods
- User interfaces

The best papers would be published in IEEE Multimedia. Also selected papers will be published in the Journal of Digital Information Management (JDIM) (http://www.dirf.org/jdim)