Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318616900> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4318616900 abstract "Abstract Recently, the pair of RGB images and depth images, which is denoted as RGB-D images, are introduced to improve their performances of Salient Object Detection(SOD), because one of the pairs may stand out at least in one modality. However, most existing State-Of-The-Art(SOTA) methods still suffer from dilemma. Firstly, the edges of predicted salient object are blurry. Secondly, how to integrate RGB-D images effectively still needs be explored. Thirdly, the quality of depth images have a strong impact on the performance of SOD so that the selection of depth images is worthy of exploring. To address the problems, in this paper, we propose a Edge-Inspired Depth Quality Evaluation Network(EDQNet), which evaluates the quality of the depth images based on the edge of ground truth, the edge of depth images and the predicted edge. More specifically, the Depth Quality Evaluation Module(DQEM) includes two parts: the depth decider and the depth aggregator. The former judges the quality of the depth images while the latter produces the weighted depth features. Then, the edge Detection Module(EDM) is proposed to predict the edge of salient object, producing the edge features. In addition, features from VGG backbone, edge features and the depth features are integrated by our Multi-Modality Feature Fusion(MMF) by using a series of composition of Hybrid Dilated Convolution(HDC). Moreover, the integrated features are fused by the Three-feature Interactive Module(TIM), Double-feature Interactive Module(DIM) and deconvolution to predict the final salient map. Our experiments on four RGB-D datasets demonstrate that our proposed EDQNet outperforms previous SOTA RGB-D SOD." @default.
- W4318616900 created "2023-01-31" @default.
- W4318616900 creator A5050163026 @default.
- W4318616900 creator A5079650655 @default.
- W4318616900 date "2023-01-31" @default.
- W4318616900 modified "2023-10-16" @default.
- W4318616900 title "A Novel Edge-Inspired Depth Quality Evaluation Network for RGB-D Salient Object Detection" @default.
- W4318616900 doi "https://doi.org/10.21203/rs.3.rs-2425669/v1" @default.
- W4318616900 hasPublicationYear "2023" @default.
- W4318616900 type Work @default.
- W4318616900 citedByCount "0" @default.
- W4318616900 crossrefType "posted-content" @default.
- W4318616900 hasAuthorship W4318616900A5050163026 @default.
- W4318616900 hasAuthorship W4318616900A5079650655 @default.
- W4318616900 hasBestOaLocation W43186169001 @default.
- W4318616900 hasConcept C11413529 @default.
- W4318616900 hasConcept C115961682 @default.
- W4318616900 hasConcept C138885662 @default.
- W4318616900 hasConcept C141268832 @default.
- W4318616900 hasConcept C153180895 @default.
- W4318616900 hasConcept C154945302 @default.
- W4318616900 hasConcept C162307627 @default.
- W4318616900 hasConcept C174576160 @default.
- W4318616900 hasConcept C193536780 @default.
- W4318616900 hasConcept C2776401178 @default.
- W4318616900 hasConcept C2780719617 @default.
- W4318616900 hasConcept C2781238097 @default.
- W4318616900 hasConcept C31972630 @default.
- W4318616900 hasConcept C41008148 @default.
- W4318616900 hasConcept C41895202 @default.
- W4318616900 hasConcept C45347329 @default.
- W4318616900 hasConcept C50644808 @default.
- W4318616900 hasConcept C82990744 @default.
- W4318616900 hasConcept C9417928 @default.
- W4318616900 hasConceptScore W4318616900C11413529 @default.
- W4318616900 hasConceptScore W4318616900C115961682 @default.
- W4318616900 hasConceptScore W4318616900C138885662 @default.
- W4318616900 hasConceptScore W4318616900C141268832 @default.
- W4318616900 hasConceptScore W4318616900C153180895 @default.
- W4318616900 hasConceptScore W4318616900C154945302 @default.
- W4318616900 hasConceptScore W4318616900C162307627 @default.
- W4318616900 hasConceptScore W4318616900C174576160 @default.
- W4318616900 hasConceptScore W4318616900C193536780 @default.
- W4318616900 hasConceptScore W4318616900C2776401178 @default.
- W4318616900 hasConceptScore W4318616900C2780719617 @default.
- W4318616900 hasConceptScore W4318616900C2781238097 @default.
- W4318616900 hasConceptScore W4318616900C31972630 @default.
- W4318616900 hasConceptScore W4318616900C41008148 @default.
- W4318616900 hasConceptScore W4318616900C41895202 @default.
- W4318616900 hasConceptScore W4318616900C45347329 @default.
- W4318616900 hasConceptScore W4318616900C50644808 @default.
- W4318616900 hasConceptScore W4318616900C82990744 @default.
- W4318616900 hasConceptScore W4318616900C9417928 @default.
- W4318616900 hasLocation W43186169001 @default.
- W4318616900 hasOpenAccess W4318616900 @default.
- W4318616900 hasPrimaryLocation W43186169001 @default.
- W4318616900 hasRelatedWork W1882467697 @default.
- W4318616900 hasRelatedWork W1985734751 @default.
- W4318616900 hasRelatedWork W2079759540 @default.
- W4318616900 hasRelatedWork W2283162247 @default.
- W4318616900 hasRelatedWork W2328068029 @default.
- W4318616900 hasRelatedWork W2412051338 @default.
- W4318616900 hasRelatedWork W2536452361 @default.
- W4318616900 hasRelatedWork W2921666650 @default.
- W4318616900 hasRelatedWork W2956571887 @default.
- W4318616900 hasRelatedWork W4320809347 @default.
- W4318616900 isParatext "false" @default.
- W4318616900 isRetracted "false" @default.
- W4318616900 workType "article" @default.