Computational models of visual attention are at the crossroad of disciplines like cognitive science, computational neuroscience, and computer vision. This paper proposes a model of attentional scanpath that is based on the principle that there are foundational laws that drive the emergence of visual attention. We devise variational laws of the eye-movement that rely on a generalized view of the Least Action Principle in physics.

Variational Laws of Visual Attention for Dynamic Scenes The authors investigate what locations in static and dynamic images tend to be attended to by humans. They derive a model by first defining three basic principles for visual attention (defined as an energy function to be minimized by the movements of the eye): (1) Eye movements are constrained by a harmonic oscillator at the borders of the image within a limited-sized retina. Using a cost function derived from these three functions, the authors derive differential equations for predicting the eye movements across static or dynamic images (depending on the starting location and initial velocity). The authors evaluate their technique quantitatively on data sets of static and dynamic scenes coupled with human eye movements. They demonstrate that their method performs comparable to the state-of-the-art.

Computational models of visual attention are at the crossroad of disciplines like cognitive science, computational neuroscience, and computer vision. This paper proposes a model of attentional scanpath that is based on the principle that there are foundational laws that drive the emergence of visual attention. We devise variational laws of the eye-movement that rely on a generalized view of the Least Action Principle in physics. In addition, the Lagrangian contains a brightness invariance term, which characterizes significantly the scanpath trajectories. We obtain differential equations of visual attention as the stationary point of the generalized action, and we propose an algorithm to estimate the model parameters.