An Architectural Model for Combining Spatial-Based and Object-Based Information for Attentive Video Analysis
Giuseppe Boccignone, Vittorio Caggiano, Angelo Marcelli, Paolo Napoletano, G. Di Fiore · 2006
We present an architectural model for the interaction between top-down, object-based information and bottom-up, spatial-based information in determining visual attention shifts. We focus in particular on how the attentive process can take into account the processing of faces and multiple moving objects. To validate the model, experiments with eye-tracked human subjects are presented and discussed.