Context-Aware Saliency Detection

Authors:
Stas Goferman;Lihi Zelnik-Manor;Ayellet Tal
Affiliations:
Israel Institute of Technology, Haifa;Israel Institute of Technology, Haifa;Israel Institute of Technology, Haifa
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2012

Citing 0
Cited 10

Quaternion-Based spectral saliency detection for eye fixation prediction

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Crowdsourced object segmentation with a game

Proceedings of the 2nd ACM international workshop on Crowdsourcing for multimedia
An edge detection with automatic scale selection approach to improve coherent visual attention model

Pattern Recognition Letters
An interactive personalized video summarization based on sketches

Proceedings of the 12th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry
GPU video retargeting with parallelized SeamCrop

Proceedings of the 5th ACM Multimedia Systems Conference
A novel approach to combine features for salient object detection using constrained particle swarm optimization

Pattern Recognition
Integration of the saliency-based seed extraction and random walks for image segmentation

Neurocomputing
Context-aware features and robust image representations

Journal of Visual Communication and Image Representation
Image categorization using a semantic hierarchy model with sparse set of salient regions

Frontiers of Computer Science: Selected Publications from Chinese Universities
Key-components: detection of salient regions on 3D meshes

The Visual Computer: International Journal of Computer Graphics

Quantified Score

Hi-index	0.14

Visualization

Abstract

We propose a new type of saliency—context-aware saliency—which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, we present a detection algorithm which is based on four principles observed in the psychological literature. The benefits of the proposed approach are evaluated in two applications where the context of the dominant objects is just as essential as the objects themselves. In image retargeting, we demonstrate that using our saliency prevents distortions in the important regions. In summarization, we show that our saliency helps to produce compact, appealing, and informative summaries.