AIMS AND SCOPE
Multimedia data, being multidimensional by nature, require appropriate approaches for their organizing and sorting. The growing number of sensors for capturing the environmental conditions in the moment of media creation enrich data with context-awareness. This unveils enormous potential for event-centred data processing.
The key idea underlying this workshop is to use events as the primary means for organizing and index media, e.g., photos, videos, news. Instead of starting from media and seeing a posteriori how to describe their contents, we organize a priori our data and knowledge in terms of events and use media to populate them, thus providing their experiential/contextual dimension. Events provide the common framework inside which the local experience-driven contextual information can not only be coded, but also shared and unified. Events have a local and a global dimension. The former allows mapping tags (conceptualizations) to media (personal experiences), while the latter allows sharing event descriptions (thus enabling social sharing and networking of events, tags and media) but also event structures across similar events, thus providing a common way to index media (social sharing and networking of event structures). In turn, the networking of events and event structures enables the creation of networked communities inside which common (global) descriptions of the world can be built and continuously enriched by the continuous flow of individual (local) descriptions.
Events have the ability to semantically encode relationships of different informational modalities. These modalities can include, but are not limited to: time, space, involved agents and objects. As a consequence, media processing based on events facilitates information perception by humans. This, in turn, decreases the individual’s effort for data analysis and decision making process. Moreover events can be used for reconstruction of missing data and for information enrichment.
The spatio-temporal component of events is key to contextual analysis. A variety of techniques have recently been presented to leverage contextual information for event-based analysis in multimedia. The content-based approach has demonstrated its weakness in the field of event analysis, especially for the event detection task. However content-based media analysis is important for object detection and recognition and can therefore play a role which is complementary to that of event- driven context recognition.
The convergence of aforementioned event analysis components, wrapped by appropriate state of the art human-computer interaction (HCI) technology, can really play a crucial role in the future of multi-media analysis.
Topics: the following aspects will be covered during the workshop:
The goal of the workshop is:
October 21-22, 2013 : Workshop
Workshop on Event-based Media Integration and Processing (EBMIP 2013)