VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search

By Simone Frintrop. Lecture Notes in Computer Science, 2006

366 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e7c2b64f04c5630c39f1855426034ae7a56453ae

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

Citations in the corpus

A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression (2010, neutral): “15 [11] and [21].”
State-of-the-Art in Visual Attention Modeling (2013, methodology): “There are at least four implementations of this model: iNVT by Itti [14], Saliency Toolbox (STB) by Walther [35], VOCUS by Frintrop [50], and a Matlab code by Harel [121].”
Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study (2013, methodology): “[21] 2005 B C 1 4 W × 1 4 H 12 Surprise-CIO: [39] 2005 I C 1 16 W × 1 16 H 13 Surprise-CIOFM: [39] 2005 B C 1 16 W × 1 16 H 14 AIM: Bruce and Tsotsos [38] 2005 I M 1 2 W × 1 2 H 15 STB: Saliency Toolbox [24] 2006 I M 1 16 W × 1 16 H 16 Le Meur: Le Meur et al.”
Center-surround divergence of feature statistics for salient object detection (2011, methodology): “Many computational models have been built according to this structure [12, 6, 24], among them one of the most popular systems, the iNVT of Itti et al.”
Attentive Systems: A Survey (2017, background): “Frintrop (2006) introduces a weighting function based on a measure of object uniqueness is applied to each map before summing up the maps for locating an object.”
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, background): “Digital Object Identiﬁer 10.1109/TIP.2015.2460013 segmentation [35], [36], image retargeting [13], [23], [24], object recognition and detection [31], [34], [42], video compression [41] and summarization [30], [32].”
Computational visual attention systems and their cognitive foundations: A survey (2010, methodology): “system VOCUS [Frintrop 2005].”
Attention, please! A survey of neural attention models in deep learning (2021, background): “VOCUS (Frintrop 2006) introduced a way to combine bottom-up and top-down attention, overcoming the limitations of the time.”