Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202761173> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3202761173 abstract "Recovering the 3D shape of an object from single-view image with deep neural network has been attracting increasing attention in the past few years. Recent approaches based on convolutional neural networks have shown excellent results on single-view image. Most of them, however, have many model’s parameters or fewer parameters with performance degradation. Therefore, in this work we propose a feature selection module to balance this problem. This module first calculates the uncertain degree map to obtain the feature coordinates which means some coarse parts needs to be corrected. Then using these coordinates, features in several feature maps are selected. Finally, use MLP Layer to obtain fine features by taking features selected as input. Training and Inference are slightly different in this module. Using this module, we achieve better performance with about 18% parameters addition and comparable performance with about 30% model’s parameters decrease based on the Pix2Vox [1] framework." @default.
- W3202761173 created "2021-10-11" @default.
- W3202761173 creator A5023274785 @default.
- W3202761173 creator A5035149238 @default.
- W3202761173 date "2021-01-01" @default.
- W3202761173 modified "2023-10-16" @default.
- W3202761173 title "3D Reconstruction from Single-View Image Using Feature Selection" @default.
- W3202761173 cites W2013599012 @default.
- W3202761173 cites W2027174336 @default.
- W3202761173 cites W2027560260 @default.
- W3202761173 cites W2342277278 @default.
- W3202761173 cites W2560722161 @default.
- W3202761173 cites W2603429625 @default.
- W3202761173 cites W2749324691 @default.
- W3202761173 cites W2768376748 @default.
- W3202761173 cites W2890382763 @default.
- W3202761173 cites W2962778872 @default.
- W3202761173 cites W3035358681 @default.
- W3202761173 cites W3104141662 @default.
- W3202761173 cites W3105863736 @default.
- W3202761173 cites W4241757451 @default.
- W3202761173 doi "https://doi.org/10.1007/978-3-030-87361-5_12" @default.
- W3202761173 hasPublicationYear "2021" @default.
- W3202761173 type Work @default.
- W3202761173 sameAs 3202761173 @default.
- W3202761173 citedByCount "0" @default.
- W3202761173 crossrefType "book-chapter" @default.
- W3202761173 hasAuthorship W3202761173A5023274785 @default.
- W3202761173 hasAuthorship W3202761173A5035149238 @default.
- W3202761173 hasConcept C115961682 @default.
- W3202761173 hasConcept C138885662 @default.
- W3202761173 hasConcept C148483581 @default.
- W3202761173 hasConcept C153180895 @default.
- W3202761173 hasConcept C154945302 @default.
- W3202761173 hasConcept C2776214188 @default.
- W3202761173 hasConcept C2776401178 @default.
- W3202761173 hasConcept C2781238097 @default.
- W3202761173 hasConcept C31972630 @default.
- W3202761173 hasConcept C41008148 @default.
- W3202761173 hasConcept C41895202 @default.
- W3202761173 hasConcept C50644808 @default.
- W3202761173 hasConcept C52622490 @default.
- W3202761173 hasConcept C81363708 @default.
- W3202761173 hasConceptScore W3202761173C115961682 @default.
- W3202761173 hasConceptScore W3202761173C138885662 @default.
- W3202761173 hasConceptScore W3202761173C148483581 @default.
- W3202761173 hasConceptScore W3202761173C153180895 @default.
- W3202761173 hasConceptScore W3202761173C154945302 @default.
- W3202761173 hasConceptScore W3202761173C2776214188 @default.
- W3202761173 hasConceptScore W3202761173C2776401178 @default.
- W3202761173 hasConceptScore W3202761173C2781238097 @default.
- W3202761173 hasConceptScore W3202761173C31972630 @default.
- W3202761173 hasConceptScore W3202761173C41008148 @default.
- W3202761173 hasConceptScore W3202761173C41895202 @default.
- W3202761173 hasConceptScore W3202761173C50644808 @default.
- W3202761173 hasConceptScore W3202761173C52622490 @default.
- W3202761173 hasConceptScore W3202761173C81363708 @default.
- W3202761173 hasLocation W32027611731 @default.
- W3202761173 hasOpenAccess W3202761173 @default.
- W3202761173 hasPrimaryLocation W32027611731 @default.
- W3202761173 hasRelatedWork W11273282 @default.
- W3202761173 hasRelatedWork W12546350 @default.
- W3202761173 hasRelatedWork W2008406 @default.
- W3202761173 hasRelatedWork W2585641 @default.
- W3202761173 hasRelatedWork W4090223 @default.
- W3202761173 hasRelatedWork W5535156 @default.
- W3202761173 hasRelatedWork W724576 @default.
- W3202761173 hasRelatedWork W8656678 @default.
- W3202761173 hasRelatedWork W9402503 @default.
- W3202761173 hasRelatedWork W1660204 @default.
- W3202761173 isParatext "false" @default.
- W3202761173 isRetracted "false" @default.
- W3202761173 magId "3202761173" @default.
- W3202761173 workType "book-chapter" @default.