Deeply Semantic Inductive Spatio-Temporal Learning
This addresses the problem of interpreting dynamic visuo-spatial data for domains like visual arts and cognitive science, but it appears incremental as it builds on existing inductive logic programming methods.
The authors introduced an inductive spatio-temporal learning framework based on inductive logic programming to handle relational features in dynamic visuo-spatial imagery, with a prototype system applied to visual arts and computational cognitive science.
We present an inductive spatio-temporal learning framework rooted in inductive logic programming. With an emphasis on visuo-spatial language, logic, and cognition, the framework supports learning with relational spatio-temporal features identifiable in a range of domains involving the processing and interpretation of dynamic visuo-spatial imagery. We present a prototypical system, and an example application in the domain of computing for visual arts and computational cognitive science.