In this paper a neural network model of visual short-term memory (VSTM) is presented. The model aims at integrating a winners-take-all type of neural network (Usher & Cohen, 1999) with Bundesens (1990) well-established mathematical theory of visual attention. We evaluate the models ability to fit experimental data from a classical whole and partial report study. Previous statistic models have successfully assessed the spatial distribution of visual attention; our neural network meets this standard and offers a neural interpretation of how objects are consolidated in VSTM at the same time. We hope that in the future, the model will be developed to fit temporally dependent phenomena like the attentional blink effect, lag-1 sparing, and attentional dwell-time.