A compositional approach increases the level of representation that can be automatically extracted and used in a visual information retrieval system. Visual information at the perceptual level is aggregated according to a set of rules. These rules reflect the specific context and transform perceptual words into phrases capturing pictorial content at a higher, and closer to the human, semantic level.
Citation:
Carlo Colombo, Alberto Del Bimbo, Pietro Pala, "Semantics in Visual Information Retrieval," IEEE Multimedia, vol. 6, no. 3, pp. 38-53, July-Sept. 1999, doi:10.1109/93.790610