- From: Raphaël Troncy <raphael.troncy@eurecom.fr>
- Date: Thu, 26 Jan 2012 09:55:53 +0100
- To: paul@ontology2.com
- CC: Kingsley Idehen <kidehen@openlinksw.com>, dbpedia-discussion@lists.sourceforge.net, "public-lod@w3.org" <public-lod@w3.org>
Dear Paul, >> The Ookaboo RDF dump is released under a CC-BY-SA license that is >> friendly to both academic and commericial use.With precision in excess >> of 0.98, Ookaboo enables entirely new applications for image search >> and classification. Thanks, great work indeed that will definitively interest the multimedia analysis community. I do have some questions: * From [1], you indicate that the data use the schema http://rdf.ontology2.com/vocab# but this URI is not derefencable. Any plan to actually publish your vocabulary? * Looking at the properties you seem to have defined, I wonder why you haven't make use of the W3C Ontology for Media Resources [2], in particular for describing the renditions of the images. Any reason? * What is the exact purpose of the namespace http://rdf.ookaboo.com/object/ ? Do you have a particular URI scheme for identifying the images according to their main topic? * The multimedia analysis mainly work with the LSCOM ontology [3]. There is a light version with only 39 visual concepts and a complete versions with hundreds of concepts. People building visual concept detectors primarily work with those concepts. Is there any link between this ontology and the visual concepts you have selected illustrated by those images? Best regards. Raphaël [1] http://rdf.ookaboo.com/data/latest/docs.html [2] http://www.w3.org/TR/mediaont-10/ [3] http://www.lscom.org/ -- Raphaël Troncy EURECOM, Multimedia Communications Department 2229, route des Crêtes, 06560 Sophia Antipolis, France. e-mail: raphael.troncy@eurecom.fr & raphael.troncy@gmail.com Tel: +33 (0)4 - 9300 8242 Fax: +33 (0)4 - 9000 8200 Web: http://www.eurecom.fr/~troncy/
Received on Thursday, 26 January 2012 08:56:30 UTC