Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Deep learning for predicting image memorability

Abstract: 

Memorability of media content such as images and videos has recently become an important research subject in computer vision. This paper presents our computation model for predicting image memorability, which is based on a deep learning architecture designed for a classification task. We exploit the use of both convolutional neural network (CNN) - based visual features and semantic features related to image captioning for the task. We train and test our model on the large-scale benchmarking memorability dataset: LaMem. Experiment result shows that the proposed computational model obtains better prediction performance than the state of the art, and even outperforms human consistency. We further investigate the genericity of our model on other memorability datasets. Finally, by validating the model on interestingness datasets, we reconfirm the uncorrelation between memorability and interestingness of images.

up
0 users have voted:

Paper Details

Authors:
Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Marquant Gwenaelle and Claire-Helene Demarty
Submitted On:
25 April 2018 - 4:30am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Ngoc Q. K. Duong
Paper Code:
ICASSP180014
Document Year:
2018
Cite

Document Files

Presentation_final.pdf

(53 downloads)

Subscribe

[1] Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Marquant Gwenaelle and Claire-Helene Demarty, "Deep learning for predicting image memorability", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3176. Accessed: May. 20, 2018.
@article{3176-18,
url = {http://sigport.org/3176},
author = {Hammad Squalli-Houssaini; Ngoc Q. K. Duong; Marquant Gwenaelle and Claire-Helene Demarty },
publisher = {IEEE SigPort},
title = {Deep learning for predicting image memorability},
year = {2018} }
TY - EJOUR
T1 - Deep learning for predicting image memorability
AU - Hammad Squalli-Houssaini; Ngoc Q. K. Duong; Marquant Gwenaelle and Claire-Helene Demarty
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3176
ER -
Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Marquant Gwenaelle and Claire-Helene Demarty. (2018). Deep learning for predicting image memorability. IEEE SigPort. http://sigport.org/3176
Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Marquant Gwenaelle and Claire-Helene Demarty, 2018. Deep learning for predicting image memorability. Available at: http://sigport.org/3176.
Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Marquant Gwenaelle and Claire-Helene Demarty. (2018). "Deep learning for predicting image memorability." Web.
1. Hammad Squalli-Houssaini, Ngoc Q. K. Duong, Marquant Gwenaelle and Claire-Helene Demarty. Deep learning for predicting image memorability [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3176