Foundations of Vision

By Frank Tong. 2018

364 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/82b69543411421f2810428a4548ac5f56e387025

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

Citations in the corpus

Preserving Color in Neural Artistic Style Transfer (2016, background): “This is motivated by the observation that visual perception is far more sensitive to changes in luminance than in color [6].”
On the Origin of Deep Learning (2017, background): “tworks. On the contrary, it makes the convolutional neural network resemble the human vision system in a deeper level. In the human vision system, blind spots (Gregory and Cavanagh, 2011) also exist (Wandell, 1995). Interesting work might be seen about linking the aws of human vision system to the d”
Controlling Perceptual Factors in Neural Style Transfer (2016, background): “This is motivated by the observation that visual perception is far more sensitive to changes in luminance than in colour [25].”
A parametric texture model based on deep convolutional features closely matches texture appearance for humans (2017, background): “The latter criterion may be important for understanding information loss in the visual system more generally (Freeman & Simoncelli, 2011; Koenderink & van Doorn, 1996; Wallis et al., 2016; Wandell, 1995).”
Saccader: Improving Accuracy of Hard Attention Models for Vision (2019, methodology): “These models are inspired by human vision, where the fovea and visual system process only a limited portion of the visual scene at high resolution [Wandell, 1995], and top-down pathways control eye movements to sequentially sample salient parts of visual scenes [Schütz et al.”
Image Quality Assessment: Unifying Structure and Texture Similarity (2020, background): “However, the HVS is a complex and highly nonlinear system [21], and most IQA measures within the error visibility framework rely on strong assumptions and simpliﬁcations ( e . g ., linear or quasi-linear models for early vision characterized by restricted visual stimuli), leading to a number of…”
Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order (2017, methodology): “technique described in [62], called contrastive equalization, was used.”