Context-aware saliency detection

We propose a new type of saliency—context-aware saliency—which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, w...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 10 vom: 01. Okt., Seite 1915-26
1. Verfasser: Goferman, Stas (VerfasserIn)
Weitere Verfasser: Zelnik-Manor, Lihi, Tal, Ayellet
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2012
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM21415355X
003 DE-627
005 20231224023020.0
007 cr uuu---uuuuu
008 231224s2012 xx |||||o 00| ||eng c
028 5 2 |a pubmed24n0714.xml 
035 |a (DE-627)NLM21415355X 
035 |a (NLM)22201056 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Goferman, Stas  |e verfasserin  |4 aut 
245 1 0 |a Context-aware saliency detection 
264 1 |c 2012 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 04.03.2013 
500 |a Date Revised 05.12.2012 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a We propose a new type of saliency—context-aware saliency—which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, we present a detection algorithm which is based on four principles observed in the psychological literature. The benefits of the proposed approach are evaluated in two applications where the context of the dominant objects is just as essential as the objects themselves. In image retargeting, we demonstrate that using our saliency prevents distortions in the important regions. In summarization, we show that our saliency helps to produce compact, appealing, and informative summaries 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Zelnik-Manor, Lihi  |e verfasserin  |4 aut 
700 1 |a Tal, Ayellet  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 34(2012), 10 vom: 01. Okt., Seite 1915-26  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:34  |g year:2012  |g number:10  |g day:01  |g month:10  |g pages:1915-26 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 34  |j 2012  |e 10  |b 01  |c 10  |h 1915-26