Hayward William G
Department of Psychology, Chinese University of Hong Kong, Hong Kong SAR, Shatin, NT, China.
Trends Cogn Sci. 2003 Oct;7(10):425-7. doi: 10.1016/j.tics.2003.08.004.
A debate on whether object representations capture isolated viewpoints or ranges of views has dominated research in object recognition in recent years, but now seems to be waning. Rather than assume a narrow model in which either structural or view information is used to recognize an object, researchers have begun to examine how these properties might be used cooperatively. A recent paper by Foster and Gilson confirms sensitivity to both types of information, which combine in an additive framework to predict recognition performance.
