A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

By Laurent Itti, Christof Koch, Ernst Niebur. 1998

Subfields: Computer Vision and Pattern Recognition, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Cognitive Science & Psychology

Citations in the corpus

BAM: Bottleneck Attention Module (2018, background): “A number of studies [8, 24, 38] have shown that attention plays an important role in human perception.”
CBAM: Convolutional Block Attention Module (2018, background): “It is well known that attention plays an important role in human perception [23,24,25].”
On the Binding Problem in Artificial Neural Networks (2020, neutral): “This facilitates an efficient control strategy to direct an attention window in an image by visiting image locations in order of decreasing saliency (Itti et al., 1998).”
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition (2017, neutral): “In computer vision, visual attention mechanisms date as far back as the work of Itti et al for object detection [14].”
VideoLSTM convolves, attends and flows for action recognition (2016, positive): “We draw inspiration from saliency, a classical topic in computer vision (Itti et al., 1998) that was recently shown to emerge from recurrent neural network architectures as well, e.”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, background): “Before the popularity of CNNs, contrast prior used to be a dominant cue for discovering salient objects, not only in computer vision community [2,7,30,43], but also in neuroscience [11] and cognitive psychology [50].”
Dynamic Computational Time for Visual Attention (2017, background): “Visual attention is a long-standing topic in computer vision [17, 18, 19].”
Bringing Semantics into Focus Using Visual Abstraction (2013, background): “Numerous works have explored related areas, including predicting the salient locations in an image [17, 26], ranking the relative importance of visible objects [1, 5, 16, 31] and semantically interpreting images [7, 18, 24, 38].”
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications (2008, background): “…such as waving trees; • cast shadows: the background model should include the shadow cast by moving objects that apparently behaves itself moving, in order to have a more accurate detection of the moving objects shape; • bootstrapping: the background model should be properly set up even in the…”
Computational visual attention systems and their cognitive foundations: A survey (2010, methodology): “Many computational attention systems focus on the computation of mainly three features: intensity, color, and orientation [Itti et al. 1998; Draper and Lionelle 2005; Sun and Fisher 2003; Ramström and Christensen 2004].”
Scale and object aware image retargeting for thumbnail browsing (2011, background): “) is the standard saliency, by which we mean the visual saliency defined in [8].”
Measuring and Predicting Importance of Objects in Our Visual World (2007, methodology): “Table 4 compares three baseline measures with our entire group of properties: area, several measures of distance from center, and several measures of saliency [7] using the SaliencyToolbox [16].”
Context-aware saliency detection (2010, background): “The biologically-motivated algorithms for saliency estimation [9, 8, 24, 3, 6, 12] are based on principle (1).”
Frequency-tuned salient region detection (2009, methodology): “The term saliency was used by Tsotsos et al. [27] and Ol-shausen et al. [25] in their work on visual attention, and by Itti et al. [16] in their work on rapid scene analysis.”
Visual Attention Guided Deep Imitation Learning (2017, methodology): “For a performance comparison we use the classic bottom-up saliency model [4] as the baseline.”