Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890137412> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2890137412 abstract "Visual Speech Recognition is the ability to interpret spoken text using video information only. To address such task automatically, recent works have employed Deep Learning and obtained high accuracy on the recognition of words and sentences uttered in controlled environments, with limited head-pose variation. However, the accuracy drops for multi-view datasets and when it comes to interpreting isolated mouth shapes, such as visemes, the values reported are considerably lower, as shorter segments of speech lack temporal and contextual information. In this work, we evaluate the applicability of synthetic datasets for assisting recognition of visemes in real-world data acquired under controlled and uncontrolled environments, using GRID and AVICAR datasets, respectively. We create two large-scale synthetic 2D datasets based on realistic 3D facial models - with near-frontal and multi-view mouth images. We perform experiments that indicate that a transfer learning approach using synthetic data can get higher accuracy than training from scratch using real data only, on both scenarios." @default.
- W2890137412 created "2018-09-27" @default.
- W2890137412 creator A5051251449 @default.
- W2890137412 creator A5064860556 @default.
- W2890137412 creator A5079262240 @default.
- W2890137412 date "2018-10-01" @default.
- W2890137412 modified "2023-10-03" @default.
- W2890137412 title "Towards View-Independent Viseme Recognition Based on CNNS and Synthetic Data" @default.
- W2890137412 cites W142945732 @default.
- W2890137412 cites W1556470778 @default.
- W2890137412 cites W1908325895 @default.
- W2890137412 cites W1982883756 @default.
- W2890137412 cites W2015143272 @default.
- W2890137412 cites W2060510034 @default.
- W2890137412 cites W2098355375 @default.
- W2890137412 cites W2113270438 @default.
- W2890137412 cites W2113814270 @default.
- W2890137412 cites W2115252128 @default.
- W2890137412 cites W2151323546 @default.
- W2890137412 cites W2163516157 @default.
- W2890137412 cites W2163973301 @default.
- W2890137412 cites W2243738093 @default.
- W2890137412 cites W2293862876 @default.
- W2890137412 cites W2474638510 @default.
- W2890137412 cites W2531409750 @default.
- W2890137412 cites W2550980560 @default.
- W2890137412 cites W2585824449 @default.
- W2890137412 cites W2741151796 @default.
- W2890137412 cites W2799525592 @default.
- W2890137412 cites W2891226622 @default.
- W2890137412 cites W2952746495 @default.
- W2890137412 doi "https://doi.org/10.1109/icip.2018.8451435" @default.
- W2890137412 hasPublicationYear "2018" @default.
- W2890137412 type Work @default.
- W2890137412 sameAs 2890137412 @default.
- W2890137412 citedByCount "2" @default.
- W2890137412 countsByYear W28901374122018 @default.
- W2890137412 countsByYear W28901374122019 @default.
- W2890137412 crossrefType "proceedings-article" @default.
- W2890137412 hasAuthorship W2890137412A5051251449 @default.
- W2890137412 hasAuthorship W2890137412A5064860556 @default.
- W2890137412 hasAuthorship W2890137412A5079262240 @default.
- W2890137412 hasConcept C119857082 @default.
- W2890137412 hasConcept C150899416 @default.
- W2890137412 hasConcept C153180895 @default.
- W2890137412 hasConcept C154945302 @default.
- W2890137412 hasConcept C155635449 @default.
- W2890137412 hasConcept C160920958 @default.
- W2890137412 hasConcept C162324750 @default.
- W2890137412 hasConcept C187691185 @default.
- W2890137412 hasConcept C187736073 @default.
- W2890137412 hasConcept C2524010 @default.
- W2890137412 hasConcept C2780451532 @default.
- W2890137412 hasConcept C28490314 @default.
- W2890137412 hasConcept C33767174 @default.
- W2890137412 hasConcept C33923547 @default.
- W2890137412 hasConcept C41008148 @default.
- W2890137412 hasConcept C51632099 @default.
- W2890137412 hasConcept C61328038 @default.
- W2890137412 hasConceptScore W2890137412C119857082 @default.
- W2890137412 hasConceptScore W2890137412C150899416 @default.
- W2890137412 hasConceptScore W2890137412C153180895 @default.
- W2890137412 hasConceptScore W2890137412C154945302 @default.
- W2890137412 hasConceptScore W2890137412C155635449 @default.
- W2890137412 hasConceptScore W2890137412C160920958 @default.
- W2890137412 hasConceptScore W2890137412C162324750 @default.
- W2890137412 hasConceptScore W2890137412C187691185 @default.
- W2890137412 hasConceptScore W2890137412C187736073 @default.
- W2890137412 hasConceptScore W2890137412C2524010 @default.
- W2890137412 hasConceptScore W2890137412C2780451532 @default.
- W2890137412 hasConceptScore W2890137412C28490314 @default.
- W2890137412 hasConceptScore W2890137412C33767174 @default.
- W2890137412 hasConceptScore W2890137412C33923547 @default.
- W2890137412 hasConceptScore W2890137412C41008148 @default.
- W2890137412 hasConceptScore W2890137412C51632099 @default.
- W2890137412 hasConceptScore W2890137412C61328038 @default.
- W2890137412 hasLocation W28901374121 @default.
- W2890137412 hasOpenAccess W2890137412 @default.
- W2890137412 hasPrimaryLocation W28901374121 @default.
- W2890137412 hasRelatedWork W1839883572 @default.
- W2890137412 hasRelatedWork W2551012455 @default.
- W2890137412 hasRelatedWork W2810134384 @default.
- W2890137412 hasRelatedWork W2889705046 @default.
- W2890137412 hasRelatedWork W2896257747 @default.
- W2890137412 hasRelatedWork W2949280030 @default.
- W2890137412 hasRelatedWork W2963218179 @default.
- W2890137412 hasRelatedWork W4205125228 @default.
- W2890137412 hasRelatedWork W4221042303 @default.
- W2890137412 hasRelatedWork W4286695298 @default.
- W2890137412 isParatext "false" @default.
- W2890137412 isRetracted "false" @default.
- W2890137412 magId "2890137412" @default.
- W2890137412 workType "article" @default.