Modeling attention to salient proto-objects

By Dirk Bernhardt-Walther, Christof Koch. Neural Networks, 2006

1,361 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/969924a4e40ac4ed6d3daca11ef8c07df78aa34b

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

Citations in the corpus

Predicting Important Objects for Egocentric Video Summarization (2015, methodology): “We see that low-level saliency detection (Walther and Koch 2006) is insufficient; its local estimates fail to find object-like regions.”
Measuring and Predicting Object Importance (2011, methodology): “We use a publicly available implementation (Walther and Koch 2006) to produce Saliency and Conspicuity Maps.”
A Benchmark of Computational Models of Saliency to Predict Human Fixations (2012, methodology): “Walther and Koch [83] extended this NVT model to attend to proto-object regions and created SaliencyToolBox (STB) Harel et al. [28] exploit the power, structure and parallel nature of graph algorithms to achieve efficient saliency computations of their Graph Based Visual Saliency model, which is bas”
Deep Visual Attention Prediction (2017, background): “Since then, many follow-up works [5], [30] have been proposed in this direction.”
An Assisted Photography Framework to Help Visually Impaired Users Properly Aim a Camera (2014, methodology): “Different situations call for different solutions, and so we chose to test several methods with a variety of street photographs [Walther and Koch 2006; Hou and Zhang 2007; Guo et al. 2008; Bian and Zhang 2008; Achanta et al. 2009].”
Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform (2008, methodology): “Model 1st 2nd 3rd 4th 5th Total PQFT 88 55 30 23 11 207 PFT 79 49 27 19 22 196 SR 73 43 32 21 18 187 NVT 81 43 23 19 10 176 STB 70 48 27 9 10 164 Table 4.”
A framework for photo-quality assessment and enhancement based on visual aesthetics (2010, methodology): “Each row shows two pairs of input and output images, the images in black background rows show the output of the saliency algorithm proposed in [ 20 ].”
Get real! Resolving the debate about equivalent social stimuli (2009, methodology): “We used the Saliency Toolbox (Walther & Koch, 2005, 2006).”
Sparse deep belief net model for visual area V2 (2007, methodology): “We used the saliency maps described by [27] to sample the van Hateren natural image data based on saliency.”
MED-NODE: A computer-assisted melanoma diagnosis system using non-dermoscopic images (2015, methodology): “In this contribution we opt for the salient point detector from Walther and Koch (2006), which is an extension of the visual attention model of Itti, Koch, and Niebur (1998).”