Matches in SemOpenAlex for { <https://semopenalex.org/work/W3115482207> ?p ?o ?g. }
- W3115482207 endingPage "56" @default.
- W3115482207 startingPage "44" @default.
- W3115482207 abstract "Previous RGB-D salient object detection (SOD) methods have widely adopted the deep learning tools to automatically strike a trade-off between RGB and depth (D). The key rationale is to take full advantage of the complementary nature between RGB and D, aiming for a much-improved SOD performance than that of using either of them solely. However, because to the D quality itself usually varies from scene to scene, such fully automatic fusion schemes may not always be helpful for the SOD task. Moreover, as an objective factor, the D quality has long been overlooked by previous work. Thus, this paper proposes a simple yet effective scheme to measure D quality in advance. The key idea is to devise a series of features in accordance with the common attributes of the high-quality D regions. To be more concrete, we advocate to conduct D quality assessments following a multi-scale methodology, which includes low-level edge consistency, mid-level regional uncertainty and high-level model variance. All these components will be computed independently and later be combined with RGB and D saliency cues to guide the selective RGBD fusion. Compared with the SOTA fusion schemes, our method can achieve better fusion result between RGB and D. Specifically, the proposed D quality measurement method is able to achieve steady performance improvements for almost 2.0% averagely." @default.
- W3115482207 created "2021-01-05" @default.
- W3115482207 creator A5030724247 @default.
- W3115482207 creator A5035153076 @default.
- W3115482207 creator A5065912071 @default.
- W3115482207 creator A5087253610 @default.
- W3115482207 creator A5091408797 @default.
- W3115482207 date "2021-04-01" @default.
- W3115482207 modified "2023-10-18" @default.
- W3115482207 title "Depth quality-aware selective saliency fusion for RGB-D image salient object detection" @default.
- W3115482207 cites W1969226866 @default.
- W3115482207 cites W2118246710 @default.
- W3115482207 cites W2337762808 @default.
- W3115482207 cites W2400170034 @default.
- W3115482207 cites W2588503511 @default.
- W3115482207 cites W2620958690 @default.
- W3115482207 cites W2765838470 @default.
- W3115482207 cites W2767623212 @default.
- W3115482207 cites W2767775878 @default.
- W3115482207 cites W2767889676 @default.
- W3115482207 cites W2793668851 @default.
- W3115482207 cites W2804923171 @default.
- W3115482207 cites W2805199679 @default.
- W3115482207 cites W2887522866 @default.
- W3115482207 cites W2907643346 @default.
- W3115482207 cites W2909381593 @default.
- W3115482207 cites W2922154534 @default.
- W3115482207 cites W2939217524 @default.
- W3115482207 cites W2943125866 @default.
- W3115482207 cites W2945643258 @default.
- W3115482207 cites W2945836307 @default.
- W3115482207 cites W2957414648 @default.
- W3115482207 cites W2963450895 @default.
- W3115482207 cites W2963529609 @default.
- W3115482207 cites W2963572583 @default.
- W3115482207 cites W2963897031 @default.
- W3115482207 cites W2964738399 @default.
- W3115482207 cites W2969377765 @default.
- W3115482207 cites W2969626490 @default.
- W3115482207 cites W2973058802 @default.
- W3115482207 cites W2987158829 @default.
- W3115482207 cites W2995160632 @default.
- W3115482207 cites W2999281281 @default.
- W3115482207 cites W3001083904 @default.
- W3115482207 cites W3006465601 @default.
- W3115482207 cites W3011951626 @default.
- W3115482207 cites W3027763298 @default.
- W3115482207 cites W3084740725 @default.
- W3115482207 cites W3087221416 @default.
- W3115482207 cites W3097336090 @default.
- W3115482207 cites W3099871687 @default.
- W3115482207 cites W3102864715 @default.
- W3115482207 cites W3105291825 @default.
- W3115482207 cites W3118710621 @default.
- W3115482207 doi "https://doi.org/10.1016/j.neucom.2020.12.071" @default.
- W3115482207 hasPublicationYear "2021" @default.
- W3115482207 type Work @default.
- W3115482207 sameAs 3115482207 @default.
- W3115482207 citedByCount "19" @default.
- W3115482207 countsByYear W31154822072021 @default.
- W3115482207 countsByYear W31154822072022 @default.
- W3115482207 countsByYear W31154822072023 @default.
- W3115482207 crossrefType "journal-article" @default.
- W3115482207 hasAuthorship W3115482207A5030724247 @default.
- W3115482207 hasAuthorship W3115482207A5035153076 @default.
- W3115482207 hasAuthorship W3115482207A5065912071 @default.
- W3115482207 hasAuthorship W3115482207A5087253610 @default.
- W3115482207 hasAuthorship W3115482207A5091408797 @default.
- W3115482207 hasConcept C103038307 @default.
- W3115482207 hasConcept C111472728 @default.
- W3115482207 hasConcept C121332964 @default.
- W3115482207 hasConcept C127413603 @default.
- W3115482207 hasConcept C138885662 @default.
- W3115482207 hasConcept C153180895 @default.
- W3115482207 hasConcept C154945302 @default.
- W3115482207 hasConcept C158525013 @default.
- W3115482207 hasConcept C173414695 @default.
- W3115482207 hasConcept C201995342 @default.
- W3115482207 hasConcept C26517878 @default.
- W3115482207 hasConcept C2776436953 @default.
- W3115482207 hasConcept C2778755073 @default.
- W3115482207 hasConcept C2779530757 @default.
- W3115482207 hasConcept C2780451532 @default.
- W3115482207 hasConcept C2780719617 @default.
- W3115482207 hasConcept C2781238097 @default.
- W3115482207 hasConcept C31972630 @default.
- W3115482207 hasConcept C38652104 @default.
- W3115482207 hasConcept C41008148 @default.
- W3115482207 hasConcept C41895202 @default.
- W3115482207 hasConcept C62520636 @default.
- W3115482207 hasConcept C82990744 @default.
- W3115482207 hasConceptScore W3115482207C103038307 @default.
- W3115482207 hasConceptScore W3115482207C111472728 @default.
- W3115482207 hasConceptScore W3115482207C121332964 @default.
- W3115482207 hasConceptScore W3115482207C127413603 @default.
- W3115482207 hasConceptScore W3115482207C138885662 @default.
- W3115482207 hasConceptScore W3115482207C153180895 @default.
- W3115482207 hasConceptScore W3115482207C154945302 @default.