Rapid natural scene categorization in the near absence of attention

By F. Li, R. VanRullen, Christof Koch, Pietro Perona. Proceedings of the National Academy of Sciences of the United States of America, 2002

834 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/9101fdb09e83a0bbfce3eb5f3d723d7e1b3e84ca

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

A quantitative theory of immediate visual recognition. (2007, background): “Recent psychophysical work suggests that performance on dual tasks can provide a diagnostic tool for characterizing tasks that do or do not involve attention (Li et al., 2002).”
Building the gist of a scene: the role of global image features in recognition. (2006, background): “Converging evidence from behavioral, imaging and computational studies suggest that, at least in early stages of processing, mechanisms involved in natural scene recognition may be independent from those involved in recognizing objects (Schyns and Oliva, 1994; Oliva and Torralba, 2001; Li et al., 20”
Self-Erasing Network for Integral Object Attention (2018, background): “In fact, we humans always ‘deliberately’ suppress the areas that we are not interested in so as to better focus on our attentions [17].”
Attention During Natural Vision Warps Semantic Representation Across the Human Brain (2013, positive): “These categories were used because they are quite distinct from one another, they occur commonly in real-world scenes, and they are common targets of visual search 12,13 .”
Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. (2006, background): “For instance, the degree of perspective or the mean depth of the space that a scene image subtends can be estimated by a configuration of low-level image features (Torralba & Oliva 2002, 2003).”
Recurrent Processing during Object Recognition (2013, background): “The predominant task used in studies citing support for purely feedforward processing involves a binary decision about whether an image contains an animal (Thorpe et al., 1996; Li et al., 2002; VanRullen and Koch, 2003).”
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex (2005, background): “, 1996] can be carried out without top-down attention [Li et al., 2002].”
Few-Shot Learning via Saliency-Guided Hallucination of Samples (2019, background): “One- and Few-shot Learning has been studied widely in computer vision in both shallow [26, 24, 9, 2, 8, 22] and deep learning scenarios [15, 36, 33, 10, 33, 34].”
Visual search (2010, background): “Holliday, I. E., & Braddick, O. J. (1991).”
Why does natural scene categorization require little attention? Exploring attentional requirements for natural and synthetic stimuli (2005, methodology): “Our goal is to probe a variety of possibilities that might reduce the high attentional requirement for performing the synthetic stimuli tasks in Li et al. (2002).”
Which is the best way to organize/classify images by content? (2007, background): “[8] later showed that little or no attention is needed for such rapid natural scene categorisation.”
Guided Search 6.0: An updated model of visual search (2021, background): “Bottom-up salience maps are based on something like this assumption (e.g., Bisley &Mirpour, 2019; Itti & Koch, 2000; Li, 2002) and, certainly, there are important general rules.”