Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385080018> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4385080018 abstract "Monocular depth estimation is a significant task in computer vision, which can be widely used in Simultaneous Localization and Mapping (SLAM) and navigation. However, the current unsupervised approaches have limitations in global information perception, especially at distant objects and the boundaries of the objects. To overcome this weakness, we propose a global-aware attention model called GlobalDepth for depth estimation, which includes two essential modules: Global Feature Extraction (GFE) and Selective Feature Fusion (SFF). GFE considers the correlation among multiple channels and refines the encoder feature by extending the receptive field of the network. Furthermore, we restructure the skip connection by employing SFF between the low-level and the high-level features in element wise, rather than simply concatenation or addition at the feature level. Our model excavates the key information and enhances the ability of global perception to predict details of the scene. Extensive experimental results demonstrate that our method reduces the absolute relative error by 10.32% compared with other state-of-the-art models on KITTI datasets." @default.
- W4385080018 created "2023-07-23" @default.
- W4385080018 creator A5027057491 @default.
- W4385080018 creator A5054957139 @default.
- W4385080018 creator A5066332856 @default.
- W4385080018 creator A5081115024 @default.
- W4385080018 date "2023-05-21" @default.
- W4385080018 modified "2023-09-24" @default.
- W4385080018 title "GlobalDepth: Global-Aware Attention Model for Unsupervised Monocular Depth Estimation" @default.
- W4385080018 cites W1901129140 @default.
- W4385080018 cites W1905829557 @default.
- W4385080018 cites W2074254947 @default.
- W4385080018 cites W2083047701 @default.
- W4385080018 cites W2117248802 @default.
- W4385080018 cites W2132947399 @default.
- W4385080018 cites W2133665775 @default.
- W4385080018 cites W2150066425 @default.
- W4385080018 cites W2194775991 @default.
- W4385080018 cites W2520707372 @default.
- W4385080018 cites W2609883120 @default.
- W4385080018 cites W2752782242 @default.
- W4385080018 cites W2916798096 @default.
- W4385080018 cites W2963412495 @default.
- W4385080018 cites W2963583471 @default.
- W4385080018 cites W2963591054 @default.
- W4385080018 cites W2963654727 @default.
- W4385080018 cites W2981518351 @default.
- W4385080018 cites W2985775862 @default.
- W4385080018 cites W2990791152 @default.
- W4385080018 cites W3034428934 @default.
- W4385080018 cites W3138768133 @default.
- W4385080018 cites W3145609993 @default.
- W4385080018 cites W3174211490 @default.
- W4385080018 cites W4206545998 @default.
- W4385080018 cites W4206764080 @default.
- W4385080018 doi "https://doi.org/10.1109/iscas46773.2023.10181346" @default.
- W4385080018 hasPublicationYear "2023" @default.
- W4385080018 type Work @default.
- W4385080018 citedByCount "0" @default.
- W4385080018 crossrefType "proceedings-article" @default.
- W4385080018 hasAuthorship W4385080018A5027057491 @default.
- W4385080018 hasAuthorship W4385080018A5054957139 @default.
- W4385080018 hasAuthorship W4385080018A5066332856 @default.
- W4385080018 hasAuthorship W4385080018A5081115024 @default.
- W4385080018 hasConcept C101738243 @default.
- W4385080018 hasConcept C108583219 @default.
- W4385080018 hasConcept C111919701 @default.
- W4385080018 hasConcept C114614502 @default.
- W4385080018 hasConcept C118505674 @default.
- W4385080018 hasConcept C138885662 @default.
- W4385080018 hasConcept C153180895 @default.
- W4385080018 hasConcept C154945302 @default.
- W4385080018 hasConcept C2776401178 @default.
- W4385080018 hasConcept C31972630 @default.
- W4385080018 hasConcept C33923547 @default.
- W4385080018 hasConcept C41008148 @default.
- W4385080018 hasConcept C41895202 @default.
- W4385080018 hasConcept C52622490 @default.
- W4385080018 hasConcept C65909025 @default.
- W4385080018 hasConcept C73555534 @default.
- W4385080018 hasConcept C87619178 @default.
- W4385080018 hasConceptScore W4385080018C101738243 @default.
- W4385080018 hasConceptScore W4385080018C108583219 @default.
- W4385080018 hasConceptScore W4385080018C111919701 @default.
- W4385080018 hasConceptScore W4385080018C114614502 @default.
- W4385080018 hasConceptScore W4385080018C118505674 @default.
- W4385080018 hasConceptScore W4385080018C138885662 @default.
- W4385080018 hasConceptScore W4385080018C153180895 @default.
- W4385080018 hasConceptScore W4385080018C154945302 @default.
- W4385080018 hasConceptScore W4385080018C2776401178 @default.
- W4385080018 hasConceptScore W4385080018C31972630 @default.
- W4385080018 hasConceptScore W4385080018C33923547 @default.
- W4385080018 hasConceptScore W4385080018C41008148 @default.
- W4385080018 hasConceptScore W4385080018C41895202 @default.
- W4385080018 hasConceptScore W4385080018C52622490 @default.
- W4385080018 hasConceptScore W4385080018C65909025 @default.
- W4385080018 hasConceptScore W4385080018C73555534 @default.
- W4385080018 hasConceptScore W4385080018C87619178 @default.
- W4385080018 hasLocation W43850800181 @default.
- W4385080018 hasOpenAccess W4385080018 @default.
- W4385080018 hasPrimaryLocation W43850800181 @default.
- W4385080018 hasRelatedWork W2592385986 @default.
- W4385080018 hasRelatedWork W2772780115 @default.
- W4385080018 hasRelatedWork W2773120646 @default.
- W4385080018 hasRelatedWork W2776466379 @default.
- W4385080018 hasRelatedWork W2785535669 @default.
- W4385080018 hasRelatedWork W2966657595 @default.
- W4385080018 hasRelatedWork W3110752836 @default.
- W4385080018 hasRelatedWork W4220775285 @default.
- W4385080018 hasRelatedWork W4281924768 @default.
- W4385080018 hasRelatedWork W4307326401 @default.
- W4385080018 isParatext "false" @default.
- W4385080018 isRetracted "false" @default.
- W4385080018 workType "article" @default.