Davies, J. (2013). Visual imagination in context: Retrieving a coherent set of labels with Coherencer. In R. West and T. Stewart (Eds.) Proceedings of the 12th International Conference on Cognitive Modeling (ICCM2013), Ottawa: Carleton University 263-268.

• SYSTEM: Coherencer
• System that modifies a list of objects so that they belong together, rather than forming an incoherent set.

BibTex Entry:

@InProceedings{VertolliDavies2013,
  author = 	 {Vertolli, Michael O. and Davies, Jim},
  title = 	 {Visual imagination in context: Retrieving a coherent set of labels with Coherencer},
  booktitle = 	 {Proceedings of the 12th International Conference on Cognitive Modeling (ICCM2013)},
  pages = 	 {263-268},
  year = 	 {2013},
  editor = 	 {West, Robert and Stewart, Terence},
  address =  {Ottawa, Carleton University}
}

Download: [ PDF ]

Abstract

A cognitive model of visual imagination will produce what we call “incoherent” results when it adds to an imagined scene that comes from multiple contexts (e.g., “arrow” and “violin” with “bow”). We approach this problem by exploring the co-occurrence of labels in images. We show that adding an incremental algorithm for examining networks of cooccurrence associations to the top-n co-occurring labels with a particular query produces greater coherence than just selecting the top-n labels or randomly selecting labels.

Back to Jim Davies's list of publications.