Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048166876> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3048166876 abstract "Since digital images are able to be encoded through the luminance-bandwidth-chrominance (YUV) mode, and the contribution of luminance information is greater than that of chrominance information for human visual perception, it can be inferred that the appropriate reduction of chrominance information in convolutional neural network does not disturb image object recognition. In this paper, we propose a new multi-scale non-uniform convolution called YuvConv, wherein the output feature map of the convolutional layer is regarded as an image. First, the output channels in the new convolution are divided into three kinds of components: Y, U, and V tensors. Then, the tensor Y is used to process luminance information, which is high-resolution and occupies more output channels. Next, the tensors U and V are low-resolution and use fewer channels to process chrominance information. Finally, the adjacent tensors (Y-U, Y-U-V, and U-V) are fused as the output of YuvConv. Experimental results indicate that the use of the YuvConv instead of the standard convolution can improve the performance of deep learning tasks, and it can also reduce memory consumption and computation cost." @default.
- W3048166876 created "2020-08-13" @default.
- W3048166876 creator A5008240552 @default.
- W3048166876 creator A5011596136 @default.
- W3048166876 creator A5080841116 @default.
- W3048166876 date "2021-01-01" @default.
- W3048166876 modified "2023-09-24" @default.
- W3048166876 title "YuvConv: Multi-Scale Non-Uniform Convolution Structure Based on YUV Color Model" @default.
- W3048166876 cites W1524680991 @default.
- W3048166876 cites W1821462560 @default.
- W3048166876 cites W2098676252 @default.
- W3048166876 cites W2109255472 @default.
- W3048166876 cites W2117539524 @default.
- W3048166876 cites W2279098554 @default.
- W3048166876 cites W2319920447 @default.
- W3048166876 cites W2335728318 @default.
- W3048166876 cites W2499540656 @default.
- W3048166876 cites W2560622558 @default.
- W3048166876 cites W2574253917 @default.
- W3048166876 cites W2612445135 @default.
- W3048166876 cites W2616324011 @default.
- W3048166876 cites W2624273542 @default.
- W3048166876 cites W2886851211 @default.
- W3048166876 cites W2922433978 @default.
- W3048166876 cites W2940262938 @default.
- W3048166876 cites W2949391068 @default.
- W3048166876 cites W2954721224 @default.
- W3048166876 cites W2956265248 @default.
- W3048166876 cites W2963000224 @default.
- W3048166876 cites W2963094099 @default.
- W3048166876 cites W2963163009 @default.
- W3048166876 cites W2963241429 @default.
- W3048166876 cites W2963342610 @default.
- W3048166876 cites W2963363373 @default.
- W3048166876 cites W2963696937 @default.
- W3048166876 cites W2963722952 @default.
- W3048166876 cites W2963896595 @default.
- W3048166876 cites W2963981420 @default.
- W3048166876 cites W2964137095 @default.
- W3048166876 cites W2964299589 @default.
- W3048166876 cites W2982083293 @default.
- W3048166876 cites W2988396473 @default.
- W3048166876 cites W300523764 @default.
- W3048166876 cites W3008725350 @default.
- W3048166876 cites W3102169921 @default.
- W3048166876 cites W3118608800 @default.
- W3048166876 cites W845365781 @default.
- W3048166876 doi "https://doi.org/10.1109/tmm.2020.3013352" @default.
- W3048166876 hasPublicationYear "2021" @default.
- W3048166876 type Work @default.
- W3048166876 sameAs 3048166876 @default.
- W3048166876 citedByCount "0" @default.
- W3048166876 crossrefType "journal-article" @default.
- W3048166876 hasAuthorship W3048166876A5008240552 @default.
- W3048166876 hasAuthorship W3048166876A5011596136 @default.
- W3048166876 hasAuthorship W3048166876A5080841116 @default.
- W3048166876 hasConcept C138885662 @default.
- W3048166876 hasConcept C153180895 @default.
- W3048166876 hasConcept C154945302 @default.
- W3048166876 hasConcept C163204269 @default.
- W3048166876 hasConcept C2776401178 @default.
- W3048166876 hasConcept C31972630 @default.
- W3048166876 hasConcept C41008148 @default.
- W3048166876 hasConcept C41895202 @default.
- W3048166876 hasConcept C45347329 @default.
- W3048166876 hasConcept C50644808 @default.
- W3048166876 hasConcept C73313986 @default.
- W3048166876 hasConcept C81363708 @default.
- W3048166876 hasConceptScore W3048166876C138885662 @default.
- W3048166876 hasConceptScore W3048166876C153180895 @default.
- W3048166876 hasConceptScore W3048166876C154945302 @default.
- W3048166876 hasConceptScore W3048166876C163204269 @default.
- W3048166876 hasConceptScore W3048166876C2776401178 @default.
- W3048166876 hasConceptScore W3048166876C31972630 @default.
- W3048166876 hasConceptScore W3048166876C41008148 @default.
- W3048166876 hasConceptScore W3048166876C41895202 @default.
- W3048166876 hasConceptScore W3048166876C45347329 @default.
- W3048166876 hasConceptScore W3048166876C50644808 @default.
- W3048166876 hasConceptScore W3048166876C73313986 @default.
- W3048166876 hasConceptScore W3048166876C81363708 @default.
- W3048166876 hasFunder F4320321125 @default.
- W3048166876 hasFunder F4320334817 @default.
- W3048166876 hasFunder F4320335777 @default.
- W3048166876 hasLocation W30481668761 @default.
- W3048166876 hasOpenAccess W3048166876 @default.
- W3048166876 hasPrimaryLocation W30481668761 @default.
- W3048166876 hasRelatedWork W11424074 @default.
- W3048166876 hasRelatedWork W13187899 @default.
- W3048166876 hasRelatedWork W2988963 @default.
- W3048166876 hasRelatedWork W3238102 @default.
- W3048166876 hasRelatedWork W4783353 @default.
- W3048166876 hasRelatedWork W8340350 @default.
- W3048166876 hasRelatedWork W910914 @default.
- W3048166876 hasRelatedWork W9122165 @default.
- W3048166876 hasRelatedWork W9190101 @default.
- W3048166876 hasRelatedWork W9958333 @default.
- W3048166876 isParatext "false" @default.
- W3048166876 isRetracted "false" @default.
- W3048166876 magId "3048166876" @default.
- W3048166876 workType "article" @default.