Issue No.01 - Jan.-Mar. (2014 vol.21)
John R. Smith , IBM T. J. Watson Research Center
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MMUL.2014.8
Visual scenes require complex description and modeling that involves more than a list of words. The visual semantic concept basis is larger than the number of unique words. More efforts are needed to build out the set of visual semantic concepts.
Visualization, Scene analysis, Semantics,semantic gap, multimedia, semantic concept detection, image classification, visual taxonomy, computer vision, multimedia machine learning, WordNet
John R. Smith, "How Many Visual Concepts?", IEEE MultiMedia, vol.21, no. 1, pp. 2-3, Jan.-Mar. 2014, doi:10.1109/MMUL.2014.8