• polski
    • English
Lodz University of Technology Repository
TUL Repository
  • English 
    • polski
    • English
  • Login
View Item 
  •   Home
  • Wydawnictwa Uczelniane / TUL Press
  • TEWI 2021 (Technology, Education, Knowledge, Innovation)
  • Rozdziały
  • View Item
  •   Home
  • Wydawnictwa Uczelniane / TUL Press
  • TEWI 2021 (Technology, Education, Knowledge, Innovation)
  • Rozdziały
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Prediction of Natural Image Saliency for Synthetic Images

Thumbnail
View/Open
Pred_natur_Rudak_Rynkiewicz_TEWI_2021.pdf (2.431Mb)
Date
2021
Author
Rudak, Ewa
Rynkiewicz, Filip
Daszuta, Marcin
Sturgulewski, Łukasz
Lazarek, Jagoda
Metadata
Show full item record
Abstract
Numerous saliency models are being developed with the use ofneural networks and are capable of combining various features and predicting the saliency values with great results. In fact, it might be difficult to replace the possibilities of artificial intelligence applied to algorithms responsible for predicting saliency. However, the low-level features are still important and should not be removed completely from new saliency models. This work shows that carefully chosen and integrated features, including a deep learning based one, can be used for saliency prediction. The integration is obtained by using Multiple Kernel Learning. This solution is quite effective, as compared to a few other models tested on the same dataset.
URI
http://hdl.handle.net/11652/4031
https://doi.org/10.34658/9788366741102.11
Collections
  • Książki, monografie, podręczniki, rozdziały (WEEIiA) [124]
  • Książki, monografie, podręczniki, rozdziały (WFTIiMS) [54]
  • Rozdziały [15]

DSpace software copyright © 2002-2016  DuraSpace
Contact Us | Send Feedback
Theme by 
Atmire NV
 

 

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

DSpace software copyright © 2002-2016  DuraSpace
Contact Us | Send Feedback
Theme by 
Atmire NV