Article

Visual Attention Through Uncertainty Minimization in Recurrent Generative Models

2020-02-14

Abstract excerpt

Allocating visual attention through saccadic eye movements is a key ability of intelligent agents. Attention is both influenced through bottom-up stimulus properties as well as top-down task demands. The interaction of these two attention mechanisms is not yet fully understood. A parsimonious reconciliation posits that both processes serve the minimization of predictive uncertainty. We propose a recurrent generati...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 0096ebfd-5235-5068-8f53-154766286040
DOI: 10.1101/2020.02.14.948992

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Visual Attention Through Uncertainty Minimization in Recurrent Generative ModelsDOI 10.1101/2020.02.14.948992Read

Deep Learning Neural Networks as a Component of a Model of Saccadic GenerationSemantic proximity Read

Humans adapt their anticipatory eye movements to the volatility of visual motion properties.Semantic proximity Read

A Mathematical Model of Exploration and Exploitation in Natural Scene ViewingSemantic proximity Read

A Predictive Processing Account of Bottom-Up Visual Saliency Using Cross-Predicting AutoencodersSemantic proximity Read

Humans adapt their anticipatory eye movements to the volatility of visual motion propertiesSemantic proximity Read

Coupling of saccade plans to endogenous attention during urgent choicesSemantic proximity Read

Neural signatures of associational cortex emerge in a goal-directed model of visual searchSemantic proximity Read

Horizontal saccade bias results from combination of saliency anisotropies and egocentric biasesSemantic proximity Read

Modeling Attention and Binding in the Brain through Bidirectional Recurrent GatingSemantic proximity Read

Integrating Ideal Bayesian Searcher and Neural Networks Models for Eye Movement Prediction in a Hybrid Search TaskSemantic proximity Read

Sparse mixed codes on shared manifolds for human-like spatial attention in artificial neural networksSemantic proximity Read

Knowledge-driven perceptual organization reshapes information sampling via eye movementsSemantic proximity Read