Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217020749> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3217020749 endingPage "108468" @default.
- W3217020749 startingPage "108468" @default.
- W3217020749 abstract "Incorporating the depth (D) information to RGB images has proven the effectiveness and robustness in semantic segmentation. However, the fusion between them is not trivial due to their inherent physical meaning discrepancy, in which RGB represents RGB information but D depth information. In this paper, we propose a co-attention network (CANet) to build sound interaction between RGB and depth features. The key part in the CANet is the co-attention fusion part. It includes three modules. Specifically, the position and channel co-attention fusion modules adaptively fuse RGB and depth features in spatial and channel dimensions. An additional fusion co-attention module further integrates the outputs of the position and channel co-attention fusion modules to obtain a more representative feature which is used for the final semantic segmentation. Extensive experiments witness the effectiveness of the CANet in fusing RGB and depth features, achieving state-of-the-art performance on two challenging RGB-D semantic segmentation datasets, i.e., NYUDv2 and SUN-RGBD." @default.
- W3217020749 created "2021-12-06" @default.
- W3217020749 creator A5028027471 @default.
- W3217020749 creator A5030735995 @default.
- W3217020749 creator A5039831654 @default.
- W3217020749 creator A5045358378 @default.
- W3217020749 creator A5048376875 @default.
- W3217020749 creator A5068533528 @default.
- W3217020749 date "2022-04-01" @default.
- W3217020749 modified "2023-10-17" @default.
- W3217020749 title "CANet: Co-attention network for RGB-D semantic segmentation" @default.
- W3217020749 cites W1961891967 @default.
- W3217020749 cites W2320788478 @default.
- W3217020749 cites W2412782625 @default.
- W3217020749 cites W2903642350 @default.
- W3217020749 cites W2963881378 @default.
- W3217020749 cites W3033841690 @default.
- W3217020749 doi "https://doi.org/10.1016/j.patcog.2021.108468" @default.
- W3217020749 hasPublicationYear "2022" @default.
- W3217020749 type Work @default.
- W3217020749 sameAs 3217020749 @default.
- W3217020749 citedByCount "33" @default.
- W3217020749 countsByYear W32170207492022 @default.
- W3217020749 countsByYear W32170207492023 @default.
- W3217020749 crossrefType "journal-article" @default.
- W3217020749 hasAuthorship W3217020749A5028027471 @default.
- W3217020749 hasAuthorship W3217020749A5030735995 @default.
- W3217020749 hasAuthorship W3217020749A5039831654 @default.
- W3217020749 hasAuthorship W3217020749A5045358378 @default.
- W3217020749 hasAuthorship W3217020749A5048376875 @default.
- W3217020749 hasAuthorship W3217020749A5068533528 @default.
- W3217020749 hasConcept C104317684 @default.
- W3217020749 hasConcept C127162648 @default.
- W3217020749 hasConcept C138885662 @default.
- W3217020749 hasConcept C153180895 @default.
- W3217020749 hasConcept C154945302 @default.
- W3217020749 hasConcept C158525013 @default.
- W3217020749 hasConcept C185592680 @default.
- W3217020749 hasConcept C2776401178 @default.
- W3217020749 hasConcept C31972630 @default.
- W3217020749 hasConcept C41008148 @default.
- W3217020749 hasConcept C41895202 @default.
- W3217020749 hasConcept C55493867 @default.
- W3217020749 hasConcept C63479239 @default.
- W3217020749 hasConcept C76155785 @default.
- W3217020749 hasConcept C82990744 @default.
- W3217020749 hasConcept C89600930 @default.
- W3217020749 hasConceptScore W3217020749C104317684 @default.
- W3217020749 hasConceptScore W3217020749C127162648 @default.
- W3217020749 hasConceptScore W3217020749C138885662 @default.
- W3217020749 hasConceptScore W3217020749C153180895 @default.
- W3217020749 hasConceptScore W3217020749C154945302 @default.
- W3217020749 hasConceptScore W3217020749C158525013 @default.
- W3217020749 hasConceptScore W3217020749C185592680 @default.
- W3217020749 hasConceptScore W3217020749C2776401178 @default.
- W3217020749 hasConceptScore W3217020749C31972630 @default.
- W3217020749 hasConceptScore W3217020749C41008148 @default.
- W3217020749 hasConceptScore W3217020749C41895202 @default.
- W3217020749 hasConceptScore W3217020749C55493867 @default.
- W3217020749 hasConceptScore W3217020749C63479239 @default.
- W3217020749 hasConceptScore W3217020749C76155785 @default.
- W3217020749 hasConceptScore W3217020749C82990744 @default.
- W3217020749 hasConceptScore W3217020749C89600930 @default.
- W3217020749 hasFunder F4320321001 @default.
- W3217020749 hasFunder F4320335777 @default.
- W3217020749 hasFunder F4320335843 @default.
- W3217020749 hasLocation W32170207491 @default.
- W3217020749 hasOpenAccess W3217020749 @default.
- W3217020749 hasPrimaryLocation W32170207491 @default.
- W3217020749 hasRelatedWork W1532073221 @default.
- W3217020749 hasRelatedWork W2049632933 @default.
- W3217020749 hasRelatedWork W2107220315 @default.
- W3217020749 hasRelatedWork W2171975302 @default.
- W3217020749 hasRelatedWork W2377538627 @default.
- W3217020749 hasRelatedWork W2729046585 @default.
- W3217020749 hasRelatedWork W2770593030 @default.
- W3217020749 hasRelatedWork W3154990682 @default.
- W3217020749 hasRelatedWork W4281727072 @default.
- W3217020749 hasRelatedWork W4312219546 @default.
- W3217020749 hasVolume "124" @default.
- W3217020749 isParatext "false" @default.
- W3217020749 isRetracted "false" @default.
- W3217020749 magId "3217020749" @default.
- W3217020749 workType "article" @default.