Multimedia at your fingertips
The Internet has become a huge repository for multimedia information, i.e. a combination of audio, video and photos, from scientific presentations to music video clips. As this online treasure grows, it is important to develop easier and more efficient ways to search for relevant multimedia content. The EU-funded project 'Semantic oriented multimedia indexation and retrieval' (SOMIR) sought to address the challenge of obtaining desired multimedia information. It employed a semantic-oriented approach that considered a combination of multimedia metadata, indexing algorithms and user queries to achieve accurate searches. In more detail, the project investigated how a user's query is executed to develop more efficient content indexation, which is crucial for managing and retrieving relevant information. It looked at indexing based on algorithms that generate diverse, heterogeneous multimedia metadata. The latter could refer to language the content is written in, tools used to create it and links on the subject, enabling browsers to improve the experience of users. SOMIR improved the relevance of query results through query enhancement and/or query rewriting, as well as by indentifying the relevant algorithms to improve indexation and querying. At the end, the technology used query histories to create personalised search recommendations for users. The results of the project were published in numerous articles, notable journals and papers. They may ultimately help third parties upgrade the way multimedia content reaches its audience and enhance the information age in many ways.
