Modelling Task-Dependent Eye Guidance to Objects in Pictures

Abstract

We introduce a model of attentional eye guidance based on the rationale that the deployment of gaze is to be considered in the context of a general actionperception loop relying on two strictly intertwined processes: sensory processing, depending on current gaze position, identifies sources of information that are most valuable under the given task; motor processing links such information with the oculomotor act by sampling the next gaze position and thus performing the gaze shift. In such a framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the payoff of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects. The different levels of the actionperception loop are represented in probabilistic form and eventually give rise to a stochastic process that generates the gaze sequence. This way the model also accounts for statistical properties of gaze shifts such as individual scan path variability. Results of the simulations are compared either with experimental data

Problems with Saliency Maps

“…The many facets of salience (and benchmarking) Despite the considerable successes that salience has had in predicting fixations at above-chance levels, it has become increasingly clear that prediction requires high-level, semanticallymeaningful elements (e.g. faces, objects and text [11,12]). Thus, prominent models of attention control posit a dichotomy between bottom-up and top-down, "endogenous" control, the latter being determined by current selection goals; in this case spotted items are selected in terms of their goal relevance, rather than physical salience.…”

Is Human Visual Activity in Simple Human-Computer Interaction Search Tasks a Lévy Flight?

“…The suggestion that the human visual activity may be successfully modelled by Lévy flights or some combinations of Lévy flights and other processes appeared also in a number of other papers e.g. Stephen et al 2009, Shinde et al (2011, Boccignone and Ferraro (2013), Liu et al (2013) or lately Clavelli et al (2014).…”

Semi-automatic Text and Graphics Extraction of Manga Using Eye Tracking Information

“…The efficiency of combining text and speech balloon features to extract both of them has been highlighted recently [16]. The benefits of using eye-tracker for text extraction has already been demonstrated as in [2], [17]. Few work about comic character extraction have been published until now.…”