Computational visual attention systems and their cognitive foundations: A survey

By Simone Frintrop, Erich Rome, Henrik Iskov Christensen. On Tap, 2010

472 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/d3de76b9f72c5cc9c3257217801daccc5941b71b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention (2020, background): “While paraphrasing is the task of “conveying the same meaning, but with different expressions” [9, 18, 41], summarization deals with extracting or abstracting the key points of a larger input sequence [21, 73, 33].”
Social eye gaze in human-robot interaction (2017, background): “These models generally have a similar structure: They compute the saliencies of several features in parallel, then combine these saliencies into a single saliency map (Frintrop, Rome, & Christensen, 2010).”
Attentional Correlation Filter Network for Adaptive Visual Tracking (2017, methodology): “The importance of attentional mechanisms of the human visual system is highlighted by recent trends in neuroscience research [13,14,28], as well as by theoretical work on the computational aspects of visual attention [12, 34].”
A Benchmark of Computational Models of Saliency to Predict Human Fixations (2012, background): “[21] which covers models up to about 2005.”
State-of-the-Art in Visual Attention Modeling (2013, background): “For a review on computational models of visual attention in general, including biased competition [10], selective tuning [15], normalization models of attention [181], and many others; please refer to [8].”
An Assisted Photography Framework to Help Visually Impaired Users Properly Aim a Camera (2014, background): “The number, type, and combination strategy of features used for estimating saliency in images is a problem of its own [Frintrop et al. 2010].”
Predicting the Driver's Focus of Attention: The DR(eye)VE Project (2017, background): “Indeed, visual attention has been approached by psychologists, neurobiologists and computer scientists, making the field highly interdisciplinary [20].”
New Contour Cue-Based Hybrid Sparse Learning for Salient Object Detection (2019, background): “As an interdisciplinary research direction, visual saliency has been broadly studied from biological, psychological, and computational perspectives for decades [23].”
DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations (2015, background): “On the contrary, the top-down attention mechanism is driven by internal factors such as subject’s prior knowledge, expectations and the task at hand, making it situational and highly subjective [2].”
Center-surround divergence of feature statistics for salient object detection (2011, background): “While these systems have obtained good results in simulating human eye movements and in applications ranging from object recognition to robotics [7], one problem is that the fusion of feature channels with per se not comparable properties is usually somewhat arbitrary.”