The paper presents a biologically plausible model of an attentional mechanism that forms position- and scale-invariant representations of objects in the visual world. The model relies on control neurons to dynamically modify synaptic strengths in intracortical connections, selectively routing information from a windowed region of primary visual cortex (V1) to higher cortical areas while preserving local spatial relationships. This enables attended objects to be represented in higher cortical areas within an object-centered reference frame that is position and scale invariant. The pulvinar is hypothesized to provide control signals for routing information through the cortex. The dynamics of control neurons are governed by simple differential equations, and the model respects key neurophysiological, neuroanatomical, and psychophysical data. The model makes experimentally testable predictions and is designed to address the computational challenges of pattern recognition in the visual system.The paper presents a biologically plausible model of an attentional mechanism that forms position- and scale-invariant representations of objects in the visual world. The model relies on control neurons to dynamically modify synaptic strengths in intracortical connections, selectively routing information from a windowed region of primary visual cortex (V1) to higher cortical areas while preserving local spatial relationships. This enables attended objects to be represented in higher cortical areas within an object-centered reference frame that is position and scale invariant. The pulvinar is hypothesized to provide control signals for routing information through the cortex. The dynamics of control neurons are governed by simple differential equations, and the model respects key neurophysiological, neuroanatomical, and psychophysical data. The model makes experimentally testable predictions and is designed to address the computational challenges of pattern recognition in the visual system.