Measuring and modifying the intrinsic memorability of images
Name
933239294-MIT.pdf
Description
Full printable version
Size
9.87 MB
Format
Adobe PDF
Checksum (MD5)
e5fe07b109222ed4698efd928293eec7
Author(s)
Raju, Akhil (Akhil G.)
Advisor(s)
Antonio Torralba.
Date Issued
2015
Publisher
Massachusetts Institute of Technology
Abstract
this thesis, I developed and carried out a procedure to measure the memorability of an image by running hundreds of human-trials and making use of a custom designed image dataset, the Mem60k dataset. The large store of ground-truth memorability data enabled a variety of insights and applications. The data revealed information about what qualities (emotional content, aesthetic appeal, etc.) in an image make it memorable. Convolutional neural networks (CNNs) trained on the data could predict an image's relative memorability with high accuracy. CNNs could also generate memorability heat maps which pinpoint which parts of an image are memorable. Finally, with additional usage of a massive image database, I designed a pipeline that could modify the intrinsic memorability of an image. The performance of each application was tested and measured by running further human trials.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 57-59).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
Persistent DSpace Link
