|
Workshop proceedings are available here.
Finding geographically-based information constitutes a common use of Web search engines, for a variety of user needs. With the rapid growth of the volume of geographically-related information on the Web, efficient and adaptable ways of tagging, browsing and accessing relevant documents still needs to be found. Structuring and mashing-up geographic information from different Web data sources is one appealing alternative to long term efforts of manually creating large scale geographic resources such as The Alexandria Digital Library or Geonames, whose constructions are costly and not necessarily adapted to specific applications.
Efficient automatic geographical information structuring methods involve coping with a wide diversity and huge volumes of geographically relevant documents. Consider Wikipedia (over 200,000 geo-referenced articles for the English version), or Flickr (over 50 million geo-referenced pictures) or Yahoo! Trip Planner (over 159,000 publicly available trip descriptions). These sites include disparate text, images and geo-localisation information. Exploiting this information requires mixing different competences: information retrieval and ranking, natural language processing, image processing, geographic information extraction…
Many hard research questions related to geographic information retrieval (GIR) remain unsolved. We will address the following in this workshop:
- How to move from raw data to structured knowledge? How can we identify, disambiguate, localize, categorize and rank geographic names?
- What are the best ways to process geographically relevant multimedia documents? How to combine text, image and/or video analysis in coherent frameworks?
- How to exploit user contributed information? How to filter out noise introduce and how to leverage information at a community level?
- How to adapt and/or personalize the presentation of results?
This workshop brings elements of answers to these research questions and is a meeting point for different disciplines interested in geographic information. It focuses on combining analysis skills to improve geographic information processing. We welcome researchers from communities as diverse as geographic information extraction and retrieval, context aware devices, geographic information systems or image processing to discuss their ideas in a challenging and interactive forum.
We solicit submissions addressing the following topics:
- Web-scale geographic information retrieval frameworks
- Geo-referenced image and video annotation and retrieval
- Ranking for geographical search
- Semi-automatic or automatic structuring of geographic information
- Location based services
- Indexing of geographically relevant multimedia documents
- Visualization of geographic information
- User studies in geographic information search
- Domain specific applications
We target the edition of a journal Special Issue or of a book as a result of the workshop.
A pdf version of the Call for Papers is available here.
|