Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949796677> ?p ?o ?g. }
- W2949796677 abstract "This paper proposes a novel saliency detection method by combining region-level saliency estimation and pixel-level saliency prediction with CNNs (denoted as CRPSD). For pixel-level saliency prediction, a fully convolutional neural network (called pixel-level CNN) is constructed by modifying the VGGNet architecture to perform multi-scale feature learning, based on which an image-to-image prediction is conducted to accomplish the pixel-level saliency detection. For region-level saliency estimation, an adaptive superpixel based region generation technique is first designed to partition an image into regions, based on which the region-level saliency is estimated by using a CNN model (called region-level CNN). The pixel-level and region-level saliencies are fused to form the final salient map by using another CNN (called fusion CNN). And the pixel-level CNN and fusion CNN are jointly learned. Extensive quantitative and qualitative experiments on four public benchmark datasets demonstrate that the proposed method greatly outperforms the state-of-the-art saliency detection approaches." @default.
- W2949796677 created "2019-06-27" @default.
- W2949796677 creator A5081658414 @default.
- W2949796677 creator A5084011858 @default.
- W2949796677 date "2016-08-18" @default.
- W2949796677 modified "2023-09-26" @default.
- W2949796677 title "Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs" @default.
- W2949796677 cites W1510835000 @default.
- W2949796677 cites W1581590495 @default.
- W2949796677 cites W1686810756 @default.
- W2949796677 cites W1849277567 @default.
- W2949796677 cites W1897243830 @default.
- W2949796677 cites W1903029394 @default.
- W2949796677 cites W1918837316 @default.
- W2949796677 cites W1920234547 @default.
- W2949796677 cites W1923594904 @default.
- W2949796677 cites W1930528368 @default.
- W2949796677 cites W1942214758 @default.
- W2949796677 cites W1944582599 @default.
- W2949796677 cites W1947031653 @default.
- W2949796677 cites W1963841606 @default.
- W2949796677 cites W1994922096 @default.
- W2949796677 cites W1996326832 @default.
- W2949796677 cites W2002781701 @default.
- W2949796677 cites W2014854862 @default.
- W2949796677 cites W2020236530 @default.
- W2949796677 cites W2020523103 @default.
- W2949796677 cites W2024713411 @default.
- W2949796677 cites W2032256331 @default.
- W2949796677 cites W2036576620 @default.
- W2949796677 cites W2037954058 @default.
- W2949796677 cites W2047670868 @default.
- W2949796677 cites W2084997728 @default.
- W2949796677 cites W2086791339 @default.
- W2949796677 cites W2097117768 @default.
- W2949796677 cites W2100470808 @default.
- W2949796677 cites W2118246710 @default.
- W2949796677 cites W2128340050 @default.
- W2949796677 cites W2137110664 @default.
- W2949796677 cites W2138046011 @default.
- W2949796677 cites W2155893237 @default.
- W2949796677 cites W2156777442 @default.
- W2949796677 cites W2161185676 @default.
- W2949796677 cites W2161236525 @default.
- W2949796677 cites W2166650627 @default.
- W2949796677 cites W2211996548 @default.
- W2949796677 cites W2332175535 @default.
- W2949796677 cites W2412782625 @default.
- W2949796677 cites W2950622378 @default.
- W2949796677 cites W2950891598 @default.
- W2949796677 cites W2952808567 @default.
- W2949796677 cites W892735016 @default.
- W2949796677 cites W2027625245 @default.
- W2949796677 doi "https://doi.org/10.48550/arxiv.1608.05186" @default.
- W2949796677 hasPublicationYear "2016" @default.
- W2949796677 type Work @default.
- W2949796677 sameAs 2949796677 @default.
- W2949796677 citedByCount "0" @default.
- W2949796677 crossrefType "posted-content" @default.
- W2949796677 hasAuthorship W2949796677A5081658414 @default.
- W2949796677 hasAuthorship W2949796677A5084011858 @default.
- W2949796677 hasBestOaLocation W29497966771 @default.
- W2949796677 hasConcept C115961682 @default.
- W2949796677 hasConcept C13280743 @default.
- W2949796677 hasConcept C138885662 @default.
- W2949796677 hasConcept C153180895 @default.
- W2949796677 hasConcept C154945302 @default.
- W2949796677 hasConcept C160633673 @default.
- W2949796677 hasConcept C185798385 @default.
- W2949796677 hasConcept C202227193 @default.
- W2949796677 hasConcept C205649164 @default.
- W2949796677 hasConcept C2776151529 @default.
- W2949796677 hasConcept C2776401178 @default.
- W2949796677 hasConcept C2779679900 @default.
- W2949796677 hasConcept C31972630 @default.
- W2949796677 hasConcept C41008148 @default.
- W2949796677 hasConcept C41895202 @default.
- W2949796677 hasConcept C81363708 @default.
- W2949796677 hasConceptScore W2949796677C115961682 @default.
- W2949796677 hasConceptScore W2949796677C13280743 @default.
- W2949796677 hasConceptScore W2949796677C138885662 @default.
- W2949796677 hasConceptScore W2949796677C153180895 @default.
- W2949796677 hasConceptScore W2949796677C154945302 @default.
- W2949796677 hasConceptScore W2949796677C160633673 @default.
- W2949796677 hasConceptScore W2949796677C185798385 @default.
- W2949796677 hasConceptScore W2949796677C202227193 @default.
- W2949796677 hasConceptScore W2949796677C205649164 @default.
- W2949796677 hasConceptScore W2949796677C2776151529 @default.
- W2949796677 hasConceptScore W2949796677C2776401178 @default.
- W2949796677 hasConceptScore W2949796677C2779679900 @default.
- W2949796677 hasConceptScore W2949796677C31972630 @default.
- W2949796677 hasConceptScore W2949796677C41008148 @default.
- W2949796677 hasConceptScore W2949796677C41895202 @default.
- W2949796677 hasConceptScore W2949796677C81363708 @default.
- W2949796677 hasLocation W29497966771 @default.
- W2949796677 hasOpenAccess W2949796677 @default.
- W2949796677 hasPrimaryLocation W29497966771 @default.
- W2949796677 hasRelatedWork W2066730339 @default.
- W2949796677 hasRelatedWork W2071139217 @default.
- W2949796677 hasRelatedWork W2090093270 @default.