ARCOMEM's aim is to help transform archives into collective memories that are more tightly integrated with their community of users and to exploit web 2.0 and the wisdom of crowds to make web archiving a more selective and meaning-based process.
Southampton's role is to investigate the use of multimedia information (particularly images and video) in the selection of information to put into these archives.
More information about Arcomem can be found on the Arcomem webpage.
The vision inspiring LivingKnowledge is to consider diversity an asset and to make it traceable, understandable and exploitable, with the goal to improve navigation and search in very large multimodal datasets (e.g., the Web itself). LivingKnowledge will study the effect of diversity and time on opinions and bias, a topic with high potential for social and economic exploitation. We envisage a future where search and navigation tools (e.g., search engines) will automatically classify and organize opinions and bias (about, e.g., global warming or the Olympic games in China) and, therefore, will produce more insightful, better organized, easier-to-understand output.
Southampton are involved in investigating how multimedia information (particularly images) can be used to disambiguate opinions in documents.
More information about LivingKnowledge can be found on the LivingKnowledge webpage.
LiveMemories is a project funded by the autonomous region of Trento in Italy, and the vision is to create a community-based archive of Trento activities, events and thoughts.
Southampton are involved in automatically analysing and annotating images.
More information about LiveMemories can be found on the LiveMemories website.
A key contribution of OpenKnowledge is to demonstrate that by shifting the emphasis to interaction (the details of which may be hidden from users) we can obtain knowledge sharing of sufficient quality for sustainable communities of practice without the barrier of complex meta-data provision prior to community formation.
As part of the Southampton deliverables, we will be investigating how multimedia knowledge can be shared within the system.
More information about OpenKnowledge can be found on the OpenKnowledge project page.
The key contribution of HealthAgents is to provide an agent-based distributed decision support system for brain tumour diagnosis and prognosis. The southampton deliverables are based around the agent-based architecture that will support the distributed data and knowledge transfer.
More information about HealthAgents can be found on the HealthAgents project page (this now redirects to the EU page about the project).
AKTive PSI is working with the Office of Public Sector Information (OPSI) to investigate how the various producers of Crown Copyright material can integrate their data sources to provide greater information value.
Memories are compelling and fundamental to our identity. They connect us with the wider world... Meanwhile, computing progresses too. Information storage has never been cheaper or abundant. The aim of Memories for Life is to bring these diverse research efforts together, to achieve synergetic and novel results.
PhotoCOPAIN deals with how visual memories (initially photographs) can be automatically tagged (annotated) with the least effort necessary on behalf of the person remembering data. It draws upon Web2.0 concepts and computer vision concepts to make rough classifications of image data.
MIAKT was a consortium that brought together expertise in medical image analysis and knowledge engineering. As part of the EPSRC's IRC funding, the project sought to investigate how these leading-edge technologies could be used to support diagnosis of breast cancer during the screening process.
The old MIAKT local page is still available on this page I maintained (this page no longer works as the database machine is no longer available).
Artiste was a consortium of computer vision experts, and European museums, and the project sought to provide means for the museums to catalogue their large collections of annotated visual data effectively.
The old local Artiste page is still available on this page I maintained (some of the download links on this page no longer work as the machine on which the resided has been decommissioned).
MAVIS was a project designed to investigate how computer vision techniques could be augmented using thesaurus techniques over a distributed architecture. Incredibly, it was far before its time, as these techniques are now being widely used in knowledge engineering.
There's a small amount of information about the internals of MAVIS on the old local page that I maintained.