The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Feature combination strategies for saliency-based visual attention systems
Open accessAbstract
Bottom-up or saliency-based visual attention allows primates to detect nonspecific conspicuous targets in cluttered scenes. A classical metaphor, derived from electrophysiological and psychophysical studies, describes attention as a rapidly shiftable ‘‘spotlight.’’ We use a model that reproduces the attentional scan paths of this spotlight. Simple multi-scale ‘‘feature maps’’ detect local spatial discontinuities in intensity, color, and orientation, and are combined into a unique ‘‘master’’ or ‘‘saliency’’ map. The saliency map is sequentially scanned, in order of decreasing saliency, by the focus of attention. We here study the problem of combining feature maps, from different visual modalities (such as color and orientation), into a unique saliency map. Four combination strategies are compared using three databases of natural color images: (1) Simple normalized summation, (2) linear combination with learned weights, (3) global nonlinear normalization followed by summation, and (4) local nonlinear competition between salient locations followed by summation. Performance was measured as the number of false detections before the most salient target was found. Strategy (1) always yielded poorest performance and (2) best performance, with a threefold to eightfold improvement in time to find a salient target. However, (2) yielded specialized systems with poor generalization. Interestingly, strategy (4) and its simplified, computationally efficient approximation (3) yielded significantly better performance than (1), with up to fourfold improvement, while preserving generality.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A feature-integration theory of attention.
Treisman, A. M., & Gelade, G. (1980) · Cognitive Psychology · doi:10.1016/0010-0285(80)90005-5 · Cited by 12,366
A model of saliency-based visual attention for rapid scene analysis
Itti, L., Koch, C., & Niebur, E. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.730558 · Cited by 11,271
Self-citationShifts in Selective Visual Attention: Towards the Underlying Neural Circuitry
Koch, C., & Ullman, S. (1987) · Matters of Intelligence · doi:10.1007/978-94-009-3833-5_5 · Cited by 3,722
Guided Search 2.0 A revised model of visual search
Wolfe, J. M. (1994) · Psychonomic Bulletin & Review · doi:10.3758/bf03200774 · Cited by 3,504
A saliency-based search mechanism for overt and covert shifts of visual attention
Itti, L., & Koch, C. (2000) · Vision Research · doi:10.1016/s0042-6989(99)00163-7 · Cited by 3,156
Self-citationNormalization of cell responses in cat striate cortex
Heeger, D. J. (1992) · Visual Neuroscience · doi:10.1017/s0952523800009640 · Cited by 1,835
Feature-based attention influences motion processing gain in macaque visual cortex
Treue, S., & Trujillo, J. C. M. (1999) · Nature · doi:10.1038/21176 · Cited by 1,465
Columnar specificity of intrinsic horizontal and corticocortical connections in cat visual cortex
Gilbert, C., & Wiesel, T. (1989) · The Journal of Neuroscience · doi:10.1523/jneurosci.09-07-02432.1989 · Cited by 1,162
Modeling visual attention via selective tuning
Tsotsos, J. K., Culhane, S. M., Kei Wai, W. Y., Lai, Y., Davis, N., & Nuflo, F. (1995) · Artificial Intelligence · doi:10.1016/0004-3702(95)00025-9 · Cited by 1,143
The representation of visual salience in monkey parietal cortex
Gottlieb, J. P., Kusunoki, M., & Goldberg, M. E. (1998) · Nature · doi:10.1038/35135 · Cited by 1,078
Cited by
Computational modelling of visual attention
Itti, L., & Koch, C. (2001) · Nature Reviews Neuroscience · doi:10.1038/35058500 · Cited by 4,733
“First, different features contribute with different strengths to perceptual saliency 53 ,and this relative feature weighting can be influenced according to the demands of the task through top-down modulation 38,54 and through training 55–58 .”
BackgroundSelf-citationModeling attention to salient proto-objects
Walther, D., & Koch, C. (2006) · Neural Networks · doi:10.1016/j.neunet.2006.10.001 · Cited by 1,249
Automatic Foveation for Video Compression Using a Neurobiological Model of Visual Attention
Itti, L. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2004.834657 · Cited by 759
Self-citationModeling the influence of task on attention
Navalpakkam, V., & Itti, L. (2005) · Vision Research · doi:10.1016/j.visres.2004.07.042 · Cited by 625
Self-citationIs bottom-up attention useful for object recognition?
Rutishauser, U., Walther, D., Koch, C., & Perona, P. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.1315142 · Cited by 592
Computational visual attention systems and their cognitive foundations: A survey
Frintrop, S., Rome, E., & Christensen, H. I. (2010) · ACM Transactions on Applied Perception · doi:10.1145/1658349.1658355 · Cited by 389
An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed
Navalpakkam, V., & Itti, L. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.54 · Cited by 369
Self-citationSearch Goal Tunes Visual Features Optimally
Navalpakkam, V., & Itti, L. (2007) · Neuron · doi:10.1016/j.neuron.2007.01.018 · Cited by 331
Self-citationQuantifying the contribution of low-level saliency to human eye movements in dynamic scenes
Itti, L. (2005) · Visual Cognition · doi:10.1080/13506280444000661 · Cited by 331
Self-citationMulti-scale Deep Learning Architectures for Person Re-identification
Qian, X., Fu, Y., Jiang, Y.-G., Xiang, T., & Xue, X. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.577 · Cited by 319
Predicting visual fixations on video based on low-level visual features
Le Meur, O., Le Callet, P., & Barba, D. (2007) · Vision Research · doi:10.1016/j.visres.2007.06.015 · Cited by 305
Depth Matters: Influence of Depth Cues on Visual Saliency
Lang, C., Nguyen, T. V., Katti, H., Yadati, K., Kankanhalli, M., & Yan, S. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33709-3_8 · Cited by 264
White, B. J., Berg, D. J., Kan, J. Y., Marino, R. A., Itti, L., & Munoz, D. P. (2017) · Nature Communications · doi:10.1038/ncomms14263 · Cited by 191
Self-citationPerformance of visually guided tasks using simulated prosthetic vision and saliency-based cues
Parikh, N., Itti, L., Humayun, M., & Weiland, J. (2013) · Journal of Neural Engineering · doi:10.1088/1741-2560/10/2/026017 · Cited by 54
Self-citationRegion-of-interest processing for electronic visual prostheses
Boyle, J. R., Maeder, A. J., & Boles, W. W. (2008) · Journal of Electronic Imaging · doi:10.1117/1.2841708 · Cited by 36
Metadata
- Authors
- Itti, L.
- Venue
- Journal of Electronic Imaging
- Publisher
- SPIE-Intl Soc Optical Eng
- Published
- 2001-01-01
- Volume
- 10
- Issue
- 1
- Pages
- 161
- ISSN
- 1017-9909 (ISSN-L)
- OpenAlex
- W2170161511
- Cited by
- 441
- References
- 22
- FWCI
- 8.90
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.