Metadata on Aesthetic Features of AV Material (Technical Document)
- Main information
-
When it comes to metadata annotation of AV material most of the (scientifically motivated) proposals usually deal with extraction of and annotation with 'information', keyword recognition or even face recognition. Interestingly enough facilitating AV material with these features is not only difficult in terms of algorithm development and costly in terms of algorithmic time consumption, but also does not at all deliver the type of metadata, visual artists are frequently asking for. A future Live Video Conductor must be enabled to compose an outgoing signal, which is enriched by several streams assembled from live feed, temporarily stored (looped) live material and related archive material. Due to its highly performative nature real-time compiling of streams of interrelated AV material clearly is a domain of visual artists like VJs. Hence the VJ scene is regarded as an important source of input and advice. During the past 9 months we asked VJs and other visual artists to put together a 'wish list' of desired AV metadata features via postings on internet platforms, emails and during personal conversations. Among other this international VJ group also included the internationally acclaimed London based 'Addictive TV' and Vienna based 4youreye. No referenced Knowhow defined WP5: Detection, Extraction and Annotation of Knowledge. University of Applied Science Cologne Richard Wages 2009-09-30 06:24 Request for more detail
- Access and Use Rights
-
Condition of access defined in response to "need to access request". Condition of use defined in response to "need to use request".
- Protection Status
-
Copyright University of Applied Sciences, Cologne. Patent Protection not sought. Licensing Protection not sought. Utility Model Protection not sought. Closed, attachment is not public
This item is not available for public download. For further information click on Request for more details above