Matches in SemOpenAlex for { <https://semopenalex.org/work/W2092921450> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W2092921450 abstract "Frequency-tuned saliency detection analyzes image saliency from the perspective of frequency domain and fully combines image segmentation method, which outputs well- defined boundaries of salient objects. However, the method ignores spatial relationships across image parts. This paper proposes an improved saliency detection method on the basis of the frequency-tuned method. In this method, we first segment the input image into regions and then analyze the image from the frequency domain. After that, we preprocess it using Gaussian filter to eliminate noise and coding artifacts. For each region, we can get saliency map in region-level based on region contrast. Finally, salient regions are selected by winner-take-all (WTA) neural network and Inhibition of Return(IOR) mechanism. The proposed salient region detection algorithm combines the virtues of frequency-tuning and region contrast. The experimental results show the feasibility and validity of this algorithm. Keywords-Image retrieval; Semantic gap; Saliency detection; Region-level saliency map; Visual attention" @default.
- W2092921450 created "2016-06-24" @default.
- W2092921450 creator A5014377619 @default.
- W2092921450 creator A5059968882 @default.
- W2092921450 creator A5089239586 @default.
- W2092921450 date "2014-01-01" @default.
- W2092921450 modified "2023-09-25" @default.
- W2092921450 title "Salient Region Detection based on Frequency-tuning and Region Contrast" @default.
- W2092921450 cites W1497599070 @default.
- W2092921450 cites W1999478155 @default.
- W2092921450 cites W2037954058 @default.
- W2092921450 cites W2100470808 @default.
- W2092921450 cites W2122762031 @default.
- W2092921450 cites W2128272608 @default.
- W2092921450 cites W2130660124 @default.
- W2092921450 cites W2142769902 @default.
- W2092921450 cites W2144764737 @default.
- W2092921450 cites W2160066518 @default.
- W2092921450 cites W2331303580 @default.
- W2092921450 doi "https://doi.org/10.2991/csss-14.2014.171" @default.
- W2092921450 hasPublicationYear "2014" @default.
- W2092921450 type Work @default.
- W2092921450 sameAs 2092921450 @default.
- W2092921450 citedByCount "1" @default.
- W2092921450 countsByYear W20929214502020 @default.
- W2092921450 crossrefType "proceedings-article" @default.
- W2092921450 hasAuthorship W2092921450A5014377619 @default.
- W2092921450 hasAuthorship W2092921450A5059968882 @default.
- W2092921450 hasAuthorship W2092921450A5089239586 @default.
- W2092921450 hasBestOaLocation W20929214501 @default.
- W2092921450 hasConcept C153180895 @default.
- W2092921450 hasConcept C154945302 @default.
- W2092921450 hasConcept C2776502983 @default.
- W2092921450 hasConcept C2780719617 @default.
- W2092921450 hasConcept C41008148 @default.
- W2092921450 hasConceptScore W2092921450C153180895 @default.
- W2092921450 hasConceptScore W2092921450C154945302 @default.
- W2092921450 hasConceptScore W2092921450C2776502983 @default.
- W2092921450 hasConceptScore W2092921450C2780719617 @default.
- W2092921450 hasConceptScore W2092921450C41008148 @default.
- W2092921450 hasLocation W20929214501 @default.
- W2092921450 hasOpenAccess W2092921450 @default.
- W2092921450 hasPrimaryLocation W20929214501 @default.
- W2092921450 hasRelatedWork W2126384842 @default.
- W2092921450 hasRelatedWork W2141018987 @default.
- W2092921450 hasRelatedWork W2393505456 @default.
- W2092921450 hasRelatedWork W2536452361 @default.
- W2092921450 hasRelatedWork W2726222394 @default.
- W2092921450 hasRelatedWork W3016204780 @default.
- W2092921450 hasRelatedWork W3022643044 @default.
- W2092921450 hasRelatedWork W4207035477 @default.
- W2092921450 hasRelatedWork W2111723525 @default.
- W2092921450 hasRelatedWork W3021014378 @default.
- W2092921450 isParatext "false" @default.
- W2092921450 isRetracted "false" @default.
- W2092921450 magId "2092921450" @default.
- W2092921450 workType "article" @default.