Components of bottom-up gaze allocation in natural images.

By Robert J. Peters, Asha Iyer, Laurent Itti, Christof Koch. Vision Research, 2005

800 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/a7447f7e6197c0875a28686efdffe4ba4beb5460

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 Molecular Biology

Citations in the corpus

Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics (2013, methodology): “Itti’s model [12] represents the cognitive approach.”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, methodology): “The Normalized Scanpath Saliency, NSS was introduced to the saliency community as a simple correspondence measure between saliency maps and ground truth, computed as the average normalized saliency at fixated locations [64].”
Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images (2014, methodology): “A small further performance gain (for AUC and EMD) can only be achieved by Boosting [4], i.e. optimally blending many top-performing algorithms from this AUC EMD sim NSS w/ C w/o C w/ C w/o C w/ C w/o C w/ C w/o C M IT 10 03 Chance – 0.4997 – 6.8160 – 0.2183 – 0.0092 Cntr 0.7933 – 3.9998 – 0.3501 – ”
Free-Lunch Saliency via Attention in Atari Agents (2019, methodology): “To evaluate this effect, we have used the Atari Human Eye-Tracking and Demonstration Dataset (Atari-HEAD) [45] as the ground truth, measuring the similarity between saliency maps and 4240 2473-9944/19/$31.00 ©2019 IEEE DOI 10.1109/ICCVW.2019.00522 human eye movements across three metrics: normalized”
The central fixation bias in scene viewing: selecting an optimal viewing position independently of motor biases and image feature distributions. (2007, background): “While a number of modifications of the basic feature-based account have been suggested (e.g., Peters et al., 2005; Torralba et al., 2006), the data presented here suggest that a significant proportion of eye movement behavior when observers view images presented on monitors may arise from a…”
Methods for comparing scanpaths and saliency maps: strengths and weaknesses (2012, background): “The normalized scanpath saliency (NSS; Peters, Iyer, Itti, & Koch, 2005) is a metric that involves a saliency map and a The first thing to do is to standardize the saliency values in order to have a zero mean and unit standard deviation.”
Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study (2013, background): “2) Normalized Scanpath Saliency (NSS): NSS [66], [67] is the average of the response values at human eye positions (xi h, y i h) in a model’s saliency map (S) that has been normalized to have zero mean and unit standard deviation.”
Predicting human gaze using low-level saliency combined with face detection (2007, background): “on a map above threshold as false alarms, and the fraction of fixated pixels above threshold as hits [29, 31].”
Computational visual attention systems and their cognitive foundations: A survey (2010, positive): “Other work comparing computational saliency with human visual attention is presented in [Ouerhani et al. 2004; Bruce and Tsotsos 2005b; Itti 2005; Peters et al. 2005; Peters and Itti 2008].”
A Benchmark of Computational Models of Saliency to Predict Human Fixations (2012, methodology): “Several authors have shown that regions of interest found by computational model of visual attention correlate with eye fixations [59] [53] [19] [29] [52] [6] [33] [57] and the reported area under receiver operating characteristic (ROC) curve, which measures how well the two correlate, has increased”
Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision? (2013, methodology): “Attention models compute where to fixate [135], [142] and”
Simultaneously Localize, Segment and Rank the Camouflaged Objects (2021, methodology): “For the discriminative region localization, we adopt the widely used fixation prediction evaluation metrics including Similarity (SIM ) [19], Linear Correlation Coefficient (CC) [23], Earth Mover’s Distance (EMD) [38], Kullback–Leibler Divergence (KLD) [21], Normalized Scanpath Saliency (NSS) [33], ”
DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations (2015, background): “Normalized Scanpath Saliency (NSS) : Normalized Scan-path Saliency is a metric speciﬁcally introduced for saliency map evaluaiton by Peters et al. [52].”
Exploiting local and global patch rarities for saliency detection (2012, methodology): “Please note that in addition to shuffled AUC, there are also some other scores that have been often used in the past, for example Normalized Scanpath Saliency (NSS) [35], KL distance [10], and Correlation Coefficient [46].”
State-of-the-Art in Visual Attention Modeling (2013, methodology): “In the following, we focus on explaining those metrics with more consensus from the literature and provide pointers for others (Percentile [134] and Fixation Saliency Method (FS) [131], [182]) for reference.”