• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations

A saliency-based search mechanism for overt and covert shifts of visual attention (2000)

by L Itti, C Koch
Venue:Vision Research
Add To MetaCart

Tools

Sorted by:
Results 1 - 10 of 641
Next 10 →

Saliency detection: A spectral residual approach

by Xiaodi Hou, Liqing Zhang - In IEEE Conference on Computer Vision and Pattern Recognition (CVPR07). IEEE Computer Society , 2007
"... The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features ..."
Abstract - Cited by 335 (10 self) - Add to MetaCart
The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features, categories, or other forms of prior knowledge of the objects. By analyzing the log-spectrum of an input image, we extract the spectral residual of an image in spectral domain, and propose a fast method to construct the corresponding saliency map in spatial domain. We test this model on both natural pictures and artificial images such as psychological patterns. The result indicate fast and robust saliency detection of our method. 1.
(Show Context)

Citation Context

... image, models had been invented in the field of machine vision. Based on Treisman’s integration theory [24], Itti and Koch proposed a saliency model that simulates the visual search process of human =-=[8, 6, 7]-=-. More recently, Walther extended the saliency model, and successfully applied it to object recognition tasks[26]. However, as a pre-processing system, these models are computationally demanding. Most...

Graph-based visual saliency

by Jonathan Harel, Christof Koch, Pietro Perona - ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 19 , 2007
"... A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: rst forming activation maps on certain feature channels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and ..."
Abstract - Cited by 277 (6 self) - Add to MetaCart
A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: rst forming activation maps on certain feature channels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and biologically plausible insofar as it is naturally parallelized. This model powerfully predicts human xations on 749 variations of 108 natural images, achieving 98 % of the ROC area of a human-based control, whereas the classical algorithms of Itti & Koch ([2], [3], [4]) achieve only 84%.
(Show Context)

Citation Context

... (iv) 0.975313 graph (ii) I 0.974592 graph (ii) ave-max 0.974578 graph (ii) graph (iii) 0.974227 graph (i) graph (iii) 0.968414 self-info I 0.841054 *Bruce & Tsotsos [5] c-s DoG 0.840968 *Itti & Koch =-=[3]-=- c-s ave-max 0.840725 *Itti, Koch, & Niebur [2] c-s NL 0.831852 *Lee, Itti, Koch, & Braun [10] 4 Discussion and Conclusion Although a novel, simple approach to an old problem is always welcome, we mus...

Learning to Predict Where Humans Look

by Tilke Judd, Krista Ehinger, Frédo Durand, Antonio Torralba
"... For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene. Where eye tracking devices are not a viable option, models of saliency can be used to predict fixation locations. Most saliency approaches are based on bottom-up com ..."
Abstract - Cited by 211 (4 self) - Add to MetaCart
For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene. Where eye tracking devices are not a viable option, models of saliency can be used to predict fixation locations. Most saliency approaches are based on bottom-up computation that does not consider top-down image semantics and often does not match actual eye movements. To address this problem, we collected eye tracking data of 15 viewers on 1003 images and use this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features. This large database of eye tracking data is publicly available with this paper. 1.
(Show Context)

Citation Context

...re. As an alternative, models of saliency have been used to measure the conspicuity of a location, or the likelihood of a location to attract the attention of human observers. Most models of saliency =-=[9]-=- [13] [8] are biologically Figure 1. Eye tracking data. We collected eye-tracking data on 1003 images from 15 viewers to use as ground truth data to train a model of saliency using machine learning. G...

Visual correlates of fixation selection: effects of scale and time

by Benjamin W. Tatler , Roland J. Baddeley , Iain D. Gilchrist , 2005
"... What distinguishes the locations that we fixate from those that we do not? To answer this question we recorded eye movements while observers viewed natural scenes, and recorded image characteristics centred at the locations that observers fixated. To investigate potential differences in the visual c ..."
Abstract - Cited by 146 (5 self) - Add to MetaCart
What distinguishes the locations that we fixate from those that we do not? To answer this question we recorded eye movements while observers viewed natural scenes, and recorded image characteristics centred at the locations that observers fixated. To investigate potential differences in the visual characteristics of fixated versus non-fixated locations, these images were transformed to make intensity, contrast, colour, and edge content explicit. Signal detection and information theoretic techniques were then used to compare fixated regions to those that were not. The presence of contrast and edge information was more strongly discriminatory than luminance or chromaticity. Fixated locations tended to be more distinctive in the high spatial frequencies. Extremes of low frequency luminance information were avoided. With prolonged viewing, consistency in fixation locations between observers decreased. In contrast to [Parkhurst, D. J., Law, K., & Niebur, E. (2002). Modeling the role of salience in the allocation of overt visual attention. Vision Research, 42 (1), 107–123] we found no change in the involvement of image features over time. We attribute this difference in our results to a systematic bias in their metric. We propose that saccade target selection involves an unchanging intermediate level representation of the scene but that the high-level interpretation of this representation changes over time.

Modeling attention to salient proto-objects

by Dirk Walther , Christof Koch , 2006
"... ..."
Abstract - Cited by 143 (0 self) - Add to MetaCart
Abstract not found

Sun: A Bayesian framework for saliency using natural statistics

by Lingyun Zhang, Matthew H. Tong, Tim K. Marks, Honghao Shan, Garrison W. Cottrell - Journal of Vision , 2008
"... We propose a definition of saliency by considering what the visual system is trying to optimize when directing attention. The resulting model is a Bayesian framework from which bottom-up saliency emerges naturally as the self-information of visual features, and overall saliency (incorporating top-do ..."
Abstract - Cited by 143 (4 self) - Add to MetaCart
We propose a definition of saliency by considering what the visual system is trying to optimize when directing attention. The resulting model is a Bayesian framework from which bottom-up saliency emerges naturally as the self-information of visual features, and overall saliency (incorporating top-down information with bottom-up saliency) emerges as the pointwise mutual information between the features and the target when searching for a target. An implementation of our framework demonstrates that our model’s bottom-up saliency maps perform as well as or better than existing algorithms in predicting people’s fixations in free viewing. Unlike existing saliency measures, which depend on the statistics of the particular image being viewed, our measure of saliency is derived from natural image statistics, obtained in advance from a collection of natural images. For this reason, we call our model SUN (Saliency Using Natural statistics). A measure of saliency based on natural image statistics, rather than based on a single test image, provides a straightforward explanation for many search asymmetries observed in humans; the statistics of a single test image lead to predictions that are not consistent with these asymmetries. In our model, saliency is computed locally, which is consistent with the neuroanatomy of the early visual system and results in an efficient algorithm with few free parameters.
(Show Context)

Citation Context

...d overt attention is still debated, but there is compelling evidence that the similarities commonly assumed may be valid (for a review, see Findlay & Gilchrist, 2003). Itti and Koch’s saliency model (=-=Itti & Koch, 2000-=-, 2001; Itti et al., 1998) is one of the earliest and the most used for comparison in later work. The model is an implementation of and expansion on the basic ideas first proposed by Koch and Ullman (...

The jackknife—a review.

by Ph.D Judith Miller , PA Haverford - Biometrika , 1974
"... The Light Beyond, By Raymond A. Moody, Jr. with Paul Perry. New York, NY: Bantam Books, 1988, 161 pp., $18.95 In his foreword to this book, Andrew Greeley, a prominent priest and sociologist, introduces his comments with the following statement: "Raymond Moody has achieved a rare feat in th ..."
Abstract - Cited by 104 (0 self) - Add to MetaCart
The Light Beyond, By Raymond A. Moody, Jr. with Paul Perry. New York, NY: Bantam Books, 1988, 161 pp., $18.95 In his foreword to this book, Andrew Greeley, a prominent priest and sociologist, introduces his comments with the following statement: "Raymond Moody has achieved a rare feat in the quest for human knowledge; he has created a paradigm." He then refers to Thomas Kuhn, who pointed out in The Structure of Scientific Revolutions that scientific revolutions occur when someone creates a new perspective, a new model, a new approach to reality. Although Greeley acknowledges that Moody did not discover the near-death experience (NDE), he contends that because Moody put a name to it in his previous bestseller Life After Life (1975), he therefore deserves credit for the new para digm that has evolved. Greeley then refers to The Light Beyond as characterized by Moody's "openness, sensitivity and modesty." This he attributes to Moody's acknowledgement that the NDE does not repre sent proof of life after death; rather, it indicates only the existence and widespread prevalence of the NDE. I must question why Greeley does not comment more on the content of the book, and why Moody felt it was appropriate to be credited with creating a new paradigm. During the last fourteen years since Life
(Show Context)

Citation Context

...ntion is often conveniently compartmentalized as “bottom up” (guided by the physical stimulus only, e.g., loudness or brightness), or “top down” (guided by past experience; Treisman and Gelade, 1980; =-=Itti and Koch, 2000-=-). However, a more fundamental feature of any attention process is that it involves suppression. Attention is often viewed as a “spotlight” (LaBerge, 1983; Eriksen and St James, 1986), perhaps because...

Spatiotemporal Sensitivity and Visual Attention for Efficient Rendering of Dynamic Environments

by Hector Yee, Sumanta Pattanaik, Donald P. Greenberg , 2001
"... INTRODUCTION Global illumination is the physically accurate calculation of lighting in an environment. It is computationally expensive for static environments and even more so for dynamic environments. Not only are many images required for an animation, but the calculation involved increases with th ..."
Abstract - Cited by 97 (1 self) - Add to MetaCart
INTRODUCTION Global illumination is the physically accurate calculation of lighting in an environment. It is computationally expensive for static environments and even more so for dynamic environments. Not only are many images required for an animation, but the calculation involved increases with the presence of moving objects. In static environments, global illumination algorithms can precompute a lighting solution and reuse it whenever the viewpoint changes, but in dynamic environments, any moving object or light potentially affects the illumination of every other object in a scene. To guarantee accuracy, the algorithm has to recompute the entire lighting solution for each frame. This paper describes a perceptually-based technique that can dramatically reduce this computational load. The technique may also be used in image based rendering, geometry level of detail selection, realistic image synthesis, video telephony and video compression. Perceptually-based rendering operat
(Show Context)

Citation Context

...of a scene or shifts of attention due to familiarity. Moreover, a task driven topdown regime can always be added later, if needed, with the use of supervised learning [Itti99a]. Itti, Koch and Niebur =-=[Itti00]-=-[Itti99a][Itti99b][Itti98] have provided a computational model to this bottom-up approach to visual attention. The model is built on a biologically plausible architecture proposed by Koch and Ullman [...

Changing your mind: On the contributions of top-down and bottom-up guidance in visual search for feature singletons

by Jeremy M. Wolfe, Serena J. Butcher, Carol Lee, Megan Hyle - Journal of Experimental Psychology: Human Perception and Performance , 2003
"... Observers, searching for targets among distractor items, guide attention with a mix of top-down information—based on observers ’ knowledge—and bottom-up information—stimulus-based and largely independent of that knowledge. There are 2 types of top-down guidance: explicit information (e.g., verbal de ..."
Abstract - Cited by 91 (0 self) - Add to MetaCart
Observers, searching for targets among distractor items, guide attention with a mix of top-down information—based on observers ’ knowledge—and bottom-up information—stimulus-based and largely independent of that knowledge. There are 2 types of top-down guidance: explicit information (e.g., verbal description) and implicit priming by preceding targets (top-down because it implies knowledge of previous searches). Experiments 1 and 2 separate bottom-up and top-down contributions to singleton search. Experiment 3 shows that priming effects are based more strongly on target than on distractor identity. Experiments 4 and 5 show that more difficult search for one type of target (color) can impair search for other types (size, orientation). Experiment 6 shows that priming guides attention and does not just modulate response. When you look at Figure 1, your attention is probably attracted to the spiky diamond. It is a salient item, and, all else being equal, salient items that are different from their neighbors tend to attract attention (Egeth, 1977; Julesz, 1986; Moraglia, 1989). The information that guided your attention to that item can be labeled as bottom-up—meaning that it did not depend on the observer’s
(Show Context)

Citation Context

...re multiple items in a search display, how is one selected for processing at any given moment? As noted, selection is based on a combination of bottom-up, stimulus-driven salience (e.g., Braun, 1994; =-=Itti & Koch, 2000-=-; Nothdurft, 2000) and top-down information about the properties of the target (e.g., Folk, Remington, & Johnston, 1992). In this article, we look at the contributions of top-down and bottom-up proces...

Quantifying the contribution of low-level saliency to human eye movements in dynamic scenes

by Laurent Itti - Visual Cognition , 2005
"... in dynamic scenes ..."
Abstract - Cited by 86 (9 self) - Add to MetaCart
in dynamic scenes
(Show Context)

Citation Context

...raphic saliency map �Figure 1), which quantitatively predicts how conspicuous every location in the input scenery is. Its implementation has been previously described in details �Koch & Ullman, 1985; =-=Itti & Koch, 2000-=-, 2001a; Itti et al., 1998). Retinal input is processed in parallel by 12 multiscale low-level feature maps, which detect local spatial discontinuities using simulated centre-surround neurons �Hubel &...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University