Introducing a unified framework for content object description

Abstract

In this paper, a novel framework for description of rich media content is introduced. Firstly, the concept of "Content Objects" is provided. Content Objects are rich media presentations, enclosing different types of media, along with real-world information and userrelated information. These highly complex presentations require a suitable description scheme in order to be searched and retrieved by end users. Therefore a novel Rich Unified Content Description is analysed, which provides a uniform descriptor for all types of Content Objects irrespective of the underlying media and accompanying information.

I-SEARCH: A Unified Framework for Multimodal Search and Retrieval

“…When a user refers to a CO, s/he directly refers to all of its constituting parts. A detailed description of CO is available at [1].…”

“…The output is a set of low-level descriptors, which are stored using a novel description format called Rich Unified Content Description (RUCoD). The RUCoD format is also analysed in [1]. RUCoD descriptors are processed using a novel manifold learning framework, producing a set of multimodal descriptors, which are efficiently indexed to facilitate faster retrieval.…”

“…Moreover, the increase of user-generated multimedia content and the number of mobile users will raise new challenges. Towards this direction, the Future Internet (FI) aims to overcome current limitations and address emerging trends including: network architectures, content and service mobility, diffusion of heterogeneous nodes and devices, mass digitisation, new forms of user-generated (multimodal) content provisioning, emergence of software as a service and interaction with improved security, trustworthiness and privacy [1]. With respect to content characteristics, the content supported by FI could be: intelligent, i.e.…”

“…FI is expected to address several limitations of CI, with respect to content, such as disembodied and non-multimodal access to content. The lack of embodiment in CI could be faced by enhanced support of multimodality, including sound, haptics, visual, gestural, physiological, toward a deeper exploitation and integration of communication and interaction through the physical, non-verbal, fullbody channels [1].…”

Context-Aware Querying for Multimodal Search Engines

“…Query results can include any available relevant content of any of the aforementioned types. This is achieved through Rich Unified Content Annotation (RUCoD), a concept that we have introduced in [19] with the main idea being the consistent description of all sorts of content using a common XML-based description format. It becomes clear that a framework like I-SEARCH faces specific challenges with regards to the user interface (UI).…”