Answers are grounded in this paper and cite their sources.
This work discusses the author suggestion for locating content in mixed-media for context-sensitive queries. Also provides examples of nontextual approach, a system for organizing digital photographs in which all of the instances of a particular person can be found based on face recognition rather than keyword matching, and compared with a conventional metadata effort that uses predictive labelling of objects in the base data set.
No takes yet. Share an insight, caveat, or question.
D. C. A. Bulterman (2004) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: