Understanding and Predicting Image Memorability at a Large Scale

@article{Khosla2015UnderstandingAP,
  title={Understanding and Predicting Image Memorability at a Large Scale},
  author={Aditya Khosla and Akhil S. Raju and Antonio Torralba and Aude Oliva},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2390-2398}
}
Progress in estimating visual memorability has been limited by the small scale and lack of variety of benchmark data. Here, we introduce a novel experimental procedure to objectively measure human memory, allowing us to build LaMem, the largest annotated image memorability dataset to date (containing 60,000 images from diverse sources). Using Convolutional Neural Networks (CNNs), we show that fine-tuned deep features outperform all other features by a large margin, reaching a rank correlation… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 97 CITATIONS, ESTIMATED 87% COVERAGE

A Deep Learning Perspective on Beauty, Sentiment, and Remembrance of Art

VIEW 6 EXCERPTS
CITES RESULTS & METHODS
HIGHLY INFLUENCED

Defining Image Memorability using the Visual Memory Schema

  • IEEE transactions on pattern analysis and machine intelligence
  • 2019
VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Guide Your Eyes : Learning Image Manipulation under Saliency Guidance

Yen-Chung Chen, Yu-Chiang Frank Wang, Wei-Chen Chiu
  • 2019
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Population response magnitude variation in inferotemporal cortex predicts image memorability

Andrew Jaegle, Vahid Mehrpour, +3 authors Nicole C. Rust
  • eLife
  • 2019
VIEW 18 EXCERPTS
CITES METHODS & BACKGROUND

Understanding and Predicting the Memorability of Outdoor Natural Scenes.

VIEW 27 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Understanding and Predicting the Memorability of Natural Scene Images

VIEW 25 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Framework of Joint Low-Rank and Sparse Regression for Image Memorability Prediction

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Increasing Image Memorability with Neural Style Transfer

  • TOMCCAP
  • 2019
VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 43 Highly Influenced Citations

  • Averaged 26 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 37 REFERENCES

SUN database: Large-scale scene recognition from abbey to zoo

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 10 EXCERPTS

What Makes a Photograph Memorable?

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
VIEW 9 EXCERPTS

Histograms of oriented gradients for human detection

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Modifying the Memorability of Face Photographs

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 4 EXCERPTS

Fully convolutional networks for semantic segmentation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 1 EXCERPT

What Makes an Object Memorable?

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 1 EXCERPT