Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

@article{Kmmerer2014DeepGI,
  title={Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet},
  author={Matthias K{\"u}mmerer and Lucas Theis and Matthias Bethge},
  journal={CoRR},
  year={2014},
  volume={abs/1411.1045}
}
Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of high-level image features such as objects. Recent seminal advances in applying deep neural networks to tasks like object recognition suggests that they are able to capture this kind of structure. However, the enormous amount of training data necessary to train these networks makes them difficult to… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 173 CITATIONS, ESTIMATED 98% COVERAGE

Computer Vision – ECCV 2018

  • Lecture Notes in Computer Science
  • 2018
VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Semantic and Contrast-Aware Saliency

  • ArXiv
  • 2018
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning Visual Importance for Graphic Designs and Data Visualizations

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Shallow and Deep Convolutional Networks for Saliency Prediction

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 5 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations

  • IEEE Transactions on Image Processing
  • 2015
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Visual saliency prediction using deep learning techniques

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

EML-NET : An Expandable Multi-Layer NETwork for Saliency Prediction

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 17 Highly Influenced Citations

  • Averaged 42 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 26 REFERENCES

Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Going deeper with convolutions

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014

Performance-optimized hierarchical models predict neural responses in higher visual cortex.

  • Proceedings of the National Academy of Sciences of the United States of America
  • 2014