SAMT 2009 | 4th International Conference on Semantic and Digital Media Technologies

Next Gen Media Search

Roelof van Zwol, Yahoo! Research Barcelona

There are several semantic sources that can be found in the Web that are either explicit, e.g. Wikipedia, or implicit, e.g. derived from Web usage data. Most of them are related to user generated content (UGC) or what is called today the Web 2.0. In this talk, he will address various problems that exist in Web-scale image search, and show how through leveraging social media, and user generated content the user search experience can be improved. These results are the work of the multimedia retrieval team at Yahoo! Research Barcelona and they are already being used in production by Yahoo! image search. In particular, he'll present the research outcomes on three topics: (1) MediaFaces, a system detecting topical facets for queries, in particular, locations, and celebrities. (2) Diversification of image search results. (3) Machine learned ranking with user clicks, text, and visual features.generated content (UGC) or what is called today the Web 2.0.

More than a thousand words

Stefan Rueger, Knowledge Media Institute, The Open University, UK

This talk will examine the challenges and opportunities of Multimedia Search, ie, finding multimedia by fragments, examples and excerpts. What is the state-of-the-art in finding known items in a huge database of images? Can your mobile phone take a picture of a statue and tell you about its artist and significance? What is the importance of geography as local context of queries? To which extent can automated image annotation from pixels help the retrieval process? Does external knowledge in terms of ontologies or other resources help the process along?