Graph-Based Visual Saliency
Explore this paper's citation graph
Summary
A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed, which powerfully predicts human fixations 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 achieve only 84%.
- Published
- 2006-12-04
- Cited by
- 3,876
- References
- 14
- Access
- Open access
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:629401
References
- Visual correlates of fixation selection: effects of scale and time.
- Attention activates winner-take-all competition among visual filters
- Visual Saliency and Attention as Random Walks on Complex Networks
- Modeling the role of salience in the allocation of overt visual attention.
- Modelling gaze shift as a constrained random walk
- Does luminance‐contrast contribute to a saliency map for overt visual attention?
- Are human scanpaths Levy flights
- Bayesian surprise attracts human attention
- A saliency-based search mechanism for overt and covert shifts of visual attention.
- Attentional Modulation of Human Pattern Discrimination Psychophysics Reproduced by a Quantitative Model
- Is bottom-up attention useful for object recognition?
- Saliency Based on Information Maximization
- Differences of monkey and human overt attention under natural conditions.
- Nuts and bolts for the social sciences
Cited by
- A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression
- Visual saliency estimation by nonlinearly integrating features using region covariances.
- What do saliency models predict?
- Improving Level Set Method for Fast Auroral Oval Segmentation
- Saliency Based Ulcer Detection for Wireless Capsule Endoscopy Diagnosis
- Introducing context-dependent and spatially-variant viewing biases in saccadic models.
- The Image torque operator for mid-Level Vision: Theory and Experiment
- Fast Approximate Matching of Cell-Phone Videos for Robust Background Subtraction
- Detections and applications of saliency on 3D surfaces by using retinex theory
- Visual Saliency Detection and its Application to Image Retrieval
- Video Object Discovery and Co-Segmentation with Extremely Weak Supervision
- Joint 2D and 3D cues for image segmentation towards robotic applications
- Visual Saliency in Video Compression and Transmission
- Modeling Spatiotemporal Correlations between Video Saliency and Gaze Dynamics
- Security analysis of image copy detection systems based on SIFT descriptors
- Semantic-oriented Object Segmentation
- Technical Section: Aesthetic photo composition by optimal crop-and-warp
- Detección de prominencia visual en imágenes mediante jerarquías de particiones
- Real-time Enhancement of Image and Video Saliency using Semantic Depth of Field
- Wavelet-based Scale Saliency
Related papers
No related papers recorded.