Networked Media and Search Systems
The multimedia search engine with a human touch.
No search is the same and no knowledge domain requirements are identical, so how can the full potential of search intelligence be exploited?
How can search computation be boosted with intuition, lateral thinking, conceptual associations, trusted opinions and domain knowledge?
How can multimedia search be provided with time-space coherence?
CUbRIK brings together IT and human intelligence, enhancing the search experience to augment precision and the relevance of reults when machine intelligence fails or is unable to remove uncertainty. The approach is not to emulate, but rather to incorporate human and social capabilities, from feature extraction to search and validation of a multimedia content and query processing system.
CUbRIK creates a "white box" version of multimedia content and query processing system.
Multimedia search is enhanced to perform entity-based time and space awareness supported by a knowledge base of spatio-temporal entities (locations, events, trends) correlated with rich semantic associations.
This capability is based on programmable pipelines able to asynchronously schedule machine jobs, crowdsourcing and GWAP-based tasks. Results from different types of activities are reconciled to augment the precision and the relevance of results.
Fields of science
Call for proposal
See other projects for this call
Funding SchemeCP - Collaborative project (generic)