Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313377498> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4313377498 endingPage "102357" @default.
- W4313377498 startingPage "102357" @default.
- W4313377498 abstract "While deep learning (DL) has been making enormous strides in lipreading areas, it is still massively underused in learning, understanding, and producing human language content. Current DL lipreading methods rely on single-channel processing and monolingual datasets, which have a limited ability to adapt to cross-language applications. Here, we propose a novel lipreading driven deep learning framework to create cross-language learning patterns. To evaluate the algorithm’s cross-language learning ability, we present a dataset CELR-200 for both Chinese and English in lipreading, containing 200-word classes with more than 80,000 samples. We also propose two Spatio-Temporal Reconstructed 3D convolutional kernels to reconstruct the 3D convolutional Spatio-Temporal relations. By using two STR-3D convolutional kernels, we present two new lipreading models, Serial-STRNet and Parallel-STRNet. These improvements reduce the number of 3D convolutional kernel parameters and improve performance, showing good performance in CELR-200 with 65.68% and 66.35%, respectively. They outperform other lipreading models, achieving an absolute improvement of 2.56% over the state-of-the-art model. Our results identify targets for future investigations and demonstrate that STR-3D convolutional kernels can provide critical insights into lipreading tasks." @default.
- W4313377498 created "2023-01-06" @default.
- W4313377498 creator A5010627630 @default.
- W4313377498 creator A5029077341 @default.
- W4313377498 date "2023-01-01" @default.
- W4313377498 modified "2023-10-14" @default.
- W4313377498 title "Cross-language lipreading by reconstructing Spatio-Temporal relations in 3D convolution" @default.
- W4313377498 cites W1983364832 @default.
- W4313377498 cites W2014621385 @default.
- W4313377498 cites W2113814270 @default.
- W4313377498 cites W2121486117 @default.
- W4313377498 cites W2136155248 @default.
- W4313377498 cites W2898926657 @default.
- W4313377498 cites W2995028981 @default.
- W4313377498 cites W3119418740 @default.
- W4313377498 cites W3193755308 @default.
- W4313377498 cites W3195938858 @default.
- W4313377498 doi "https://doi.org/10.1016/j.displa.2022.102357" @default.
- W4313377498 hasPublicationYear "2023" @default.
- W4313377498 type Work @default.
- W4313377498 citedByCount "0" @default.
- W4313377498 crossrefType "journal-article" @default.
- W4313377498 hasAuthorship W4313377498A5010627630 @default.
- W4313377498 hasAuthorship W4313377498A5029077341 @default.
- W4313377498 hasBestOaLocation W43133774981 @default.
- W4313377498 hasConcept C108583219 @default.
- W4313377498 hasConcept C114614502 @default.
- W4313377498 hasConcept C154945302 @default.
- W4313377498 hasConcept C204321447 @default.
- W4313377498 hasConcept C2524010 @default.
- W4313377498 hasConcept C28490314 @default.
- W4313377498 hasConcept C33923547 @default.
- W4313377498 hasConcept C41008148 @default.
- W4313377498 hasConcept C45347329 @default.
- W4313377498 hasConcept C50644808 @default.
- W4313377498 hasConcept C74193536 @default.
- W4313377498 hasConcept C81363708 @default.
- W4313377498 hasConcept C90805587 @default.
- W4313377498 hasConceptScore W4313377498C108583219 @default.
- W4313377498 hasConceptScore W4313377498C114614502 @default.
- W4313377498 hasConceptScore W4313377498C154945302 @default.
- W4313377498 hasConceptScore W4313377498C204321447 @default.
- W4313377498 hasConceptScore W4313377498C2524010 @default.
- W4313377498 hasConceptScore W4313377498C28490314 @default.
- W4313377498 hasConceptScore W4313377498C33923547 @default.
- W4313377498 hasConceptScore W4313377498C41008148 @default.
- W4313377498 hasConceptScore W4313377498C45347329 @default.
- W4313377498 hasConceptScore W4313377498C50644808 @default.
- W4313377498 hasConceptScore W4313377498C74193536 @default.
- W4313377498 hasConceptScore W4313377498C81363708 @default.
- W4313377498 hasConceptScore W4313377498C90805587 @default.
- W4313377498 hasFunder F4320321001 @default.
- W4313377498 hasLocation W43133774981 @default.
- W4313377498 hasOpenAccess W4313377498 @default.
- W4313377498 hasPrimaryLocation W43133774981 @default.
- W4313377498 hasRelatedWork W2731899572 @default.
- W4313377498 hasRelatedWork W2999805992 @default.
- W4313377498 hasRelatedWork W3109753704 @default.
- W4313377498 hasRelatedWork W3116150086 @default.
- W4313377498 hasRelatedWork W3129634582 @default.
- W4313377498 hasRelatedWork W3133861977 @default.
- W4313377498 hasRelatedWork W3183915377 @default.
- W4313377498 hasRelatedWork W4200173597 @default.
- W4313377498 hasRelatedWork W4312417841 @default.
- W4313377498 hasRelatedWork W4321369474 @default.
- W4313377498 hasVolume "76" @default.
- W4313377498 isParatext "false" @default.
- W4313377498 isRetracted "false" @default.
- W4313377498 workType "article" @default.