Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203507031> ?p ?o ?g. }
- W3203507031 abstract "The task of depth recovery is to calculate the depth map using only the rgb images. The existing deep network greatly compresses the resolution in the process of feature extraction, resulting in serious loss of depth information in the edge area of the object with large depth changes and the area far away from the sensor. This paper proposes a convolutional neural network based on self-attention mechanism, which can use a single rgb image to calculate its corresponding high-resolution depth map. Specifically, we use the Fully Convolutional Network with jump connections and bilinear upsampling, and add a self-attention mechanism module inside it. The self-attention mechanism module aggregates the features at each location through the weighting and selective aggregation of the features at all locations. Compared with the baseline, our method has more obvious object edge information, and also has better results on some indicators." @default.
- W3203507031 created "2021-10-11" @default.
- W3203507031 creator A5003905445 @default.
- W3203507031 creator A5011117716 @default.
- W3203507031 creator A5020541310 @default.
- W3203507031 creator A5048371289 @default.
- W3203507031 date "2021-08-20" @default.
- W3203507031 modified "2023-09-23" @default.
- W3203507031 title "Monocular Depth Recovery Based on Self-Attention Mechanism and Transfer Learning" @default.
- W3203507031 cites W1903029394 @default.
- W3203507031 cites W2124319230 @default.
- W3203507031 cites W2149933564 @default.
- W3203507031 cites W2171740948 @default.
- W3203507031 cites W2520707372 @default.
- W3203507031 cites W2798441115 @default.
- W3203507031 cites W2907670226 @default.
- W3203507031 cites W2928601293 @default.
- W3203507031 cites W2955058313 @default.
- W3203507031 cites W2961343177 @default.
- W3203507031 cites W2962807621 @default.
- W3203507031 cites W2963403868 @default.
- W3203507031 cites W2963488291 @default.
- W3203507031 cites W2963517541 @default.
- W3203507031 cites W2963583471 @default.
- W3203507031 cites W2963591054 @default.
- W3203507031 cites W2963825193 @default.
- W3203507031 cites W2973188935 @default.
- W3203507031 cites W3120644635 @default.
- W3203507031 doi "https://doi.org/10.1109/prai53619.2021.9551059" @default.
- W3203507031 hasPublicationYear "2021" @default.
- W3203507031 type Work @default.
- W3203507031 sameAs 3203507031 @default.
- W3203507031 citedByCount "1" @default.
- W3203507031 countsByYear W32035070312022 @default.
- W3203507031 crossrefType "proceedings-article" @default.
- W3203507031 hasAuthorship W3203507031A5003905445 @default.
- W3203507031 hasAuthorship W3203507031A5011117716 @default.
- W3203507031 hasAuthorship W3203507031A5020541310 @default.
- W3203507031 hasAuthorship W3203507031A5048371289 @default.
- W3203507031 hasConcept C110384440 @default.
- W3203507031 hasConcept C111919701 @default.
- W3203507031 hasConcept C115961682 @default.
- W3203507031 hasConcept C117797892 @default.
- W3203507031 hasConcept C126838900 @default.
- W3203507031 hasConcept C138885662 @default.
- W3203507031 hasConcept C141268832 @default.
- W3203507031 hasConcept C150899416 @default.
- W3203507031 hasConcept C153180895 @default.
- W3203507031 hasConcept C154945302 @default.
- W3203507031 hasConcept C15744967 @default.
- W3203507031 hasConcept C162307627 @default.
- W3203507031 hasConcept C183115368 @default.
- W3203507031 hasConcept C2776401178 @default.
- W3203507031 hasConcept C31972630 @default.
- W3203507031 hasConcept C41008148 @default.
- W3203507031 hasConcept C41895202 @default.
- W3203507031 hasConcept C52622490 @default.
- W3203507031 hasConcept C542102704 @default.
- W3203507031 hasConcept C71924100 @default.
- W3203507031 hasConcept C81363708 @default.
- W3203507031 hasConcept C82990744 @default.
- W3203507031 hasConcept C98045186 @default.
- W3203507031 hasConceptScore W3203507031C110384440 @default.
- W3203507031 hasConceptScore W3203507031C111919701 @default.
- W3203507031 hasConceptScore W3203507031C115961682 @default.
- W3203507031 hasConceptScore W3203507031C117797892 @default.
- W3203507031 hasConceptScore W3203507031C126838900 @default.
- W3203507031 hasConceptScore W3203507031C138885662 @default.
- W3203507031 hasConceptScore W3203507031C141268832 @default.
- W3203507031 hasConceptScore W3203507031C150899416 @default.
- W3203507031 hasConceptScore W3203507031C153180895 @default.
- W3203507031 hasConceptScore W3203507031C154945302 @default.
- W3203507031 hasConceptScore W3203507031C15744967 @default.
- W3203507031 hasConceptScore W3203507031C162307627 @default.
- W3203507031 hasConceptScore W3203507031C183115368 @default.
- W3203507031 hasConceptScore W3203507031C2776401178 @default.
- W3203507031 hasConceptScore W3203507031C31972630 @default.
- W3203507031 hasConceptScore W3203507031C41008148 @default.
- W3203507031 hasConceptScore W3203507031C41895202 @default.
- W3203507031 hasConceptScore W3203507031C52622490 @default.
- W3203507031 hasConceptScore W3203507031C542102704 @default.
- W3203507031 hasConceptScore W3203507031C71924100 @default.
- W3203507031 hasConceptScore W3203507031C81363708 @default.
- W3203507031 hasConceptScore W3203507031C82990744 @default.
- W3203507031 hasConceptScore W3203507031C98045186 @default.
- W3203507031 hasLocation W32035070311 @default.
- W3203507031 hasOpenAccess W3203507031 @default.
- W3203507031 hasPrimaryLocation W32035070311 @default.
- W3203507031 hasRelatedWork W2059299633 @default.
- W3203507031 hasRelatedWork W2090346739 @default.
- W3203507031 hasRelatedWork W2283162247 @default.
- W3203507031 hasRelatedWork W2412051338 @default.
- W3203507031 hasRelatedWork W2732542196 @default.
- W3203507031 hasRelatedWork W2760085659 @default.
- W3203507031 hasRelatedWork W2921666650 @default.
- W3203507031 hasRelatedWork W2940661641 @default.
- W3203507031 hasRelatedWork W3023331843 @default.
- W3203507031 hasRelatedWork W3091976719 @default.
- W3203507031 isParatext "false" @default.
- W3203507031 isRetracted "false" @default.