Prediction of Natural Image Saliency for Synthetic Images

Uproszczony widok
dc.contributor.authorRudak, Ewa
dc.contributor.authorRynkiewicz, Filip
dc.contributor.authorDaszuta, Marcin
dc.contributor.authorSturgulewski, Łukasz
dc.contributor.authorLazarek, Jagoda
dc.date.accessioned2021-10-26T10:35:32Z
dc.date.available2021-10-26T10:35:32Z
dc.date.issued2021
dc.description.abstractNumerous 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.en_EN
dc.identifier.citationRudak E., Rynkiewicz F., Daszuta M., Sturgulewski Ł., Lazarek J., Prediction of Natural Image Saliency for Synthetic Images. W: TEWI 2021 (Technology, Education, Knowledge, Innovation), Wojciechowski A. (Ed.), Napieralski P. (Ed.), Lipiński P. (Ed.)., Seria: Monografie PŁ;Nr 2378, Wydawnictwo Politechniki Łódzkiej, Łódź 2021, s. 155-169, ISBN 978-83-66741-10-2, DOI 10.34658/9788366741102.11.
dc.identifier.doi10.34658/9788366741102.11
dc.identifier.isbn978-83-66741-10-2
dc.identifier.urihttp://hdl.handle.net/11652/4031
dc.identifier.urihttps://doi.org/10.34658/9788366741102.11
dc.language.isoenen_EN
dc.page.numbers. 155-169
dc.publisherWydawnictwo Politechniki Łódzkiejpl_PL
dc.publisherLodz University of Technology Pressen_EN
dc.relation.ispartofWojciechowski A. (Ed.), Napieralski P. (Ed.), Lipiński P. (Ed.)., TEWI 2021 (Technology, Education, Knowledge, Innovation), Seria: Monografie PŁ;Nr 2378, Wydawnictwo Politechniki Łódzkiej, Łódź 2021, ISBN 978-83-66741-10-2, DOI 10.34658/9788366741102.
dc.relation.ispartofseriesMonografie Politechniki Łódzkiej; 2378pl_PL
dc.relation.ispartofseriesLodz University of Technology Monographs; 2378en_EN
dc.rightsFair use conditionen_EN
dc.rightsDla wszystkich w zakresie dozwolonego użytkupl_PL
dc.rights.licenseLUT Licenseen_EN
dc.rights.licenseLicencja PŁpl_PL
dc.subjectcomputer gamesen_EN
dc.subjectartificial intelligenceen_EN
dc.subjectimage saliencyen_EN
dc.subjectHuman Visual Attentionen_EN
dc.subjectgry komputerowepl_PL
dc.subjectsztuczna inteligencjapl_PL
dc.subjectistotność obrazupl_PL
dc.subjectuwaga wzrokowa człowiekapl_PL
dc.titlePrediction of Natural Image Saliency for Synthetic Imagesen_EN
dc.typeRozdział książkipl_PL
dc.typeBook chapteren_EN

Pliki

Oryginalne pliki
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
Pred_natur_Rudak_Rynkiewicz_TEWI_2021.pdf
Rozmiar:
2.43 MB
Format:
Adobe Portable Document Format
Opis:
Pobierz
Licencja
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
license.txt
Rozmiar:
1.71 KB
Format:
Item-specific license agreed upon to submission
Opis:
Pobierz

Kolekcje

Rozdziały
Książki, monografie, podręczniki, rozdziały (WEEIiA)
Książki, monografie, podręczniki, rozdziały (WFTIiMS)