Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897846591> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2897846591 abstract "Recently, Deep Learning-based methods have obtained high accuracy for the problem of Visual Speech Recognition. However, while good results have been reported for words and sentences, recognizing shorter segments of speech, like phones, has proven to be much more challenging due to the lack of temporal and contextual information. In this work, we address the problem of recognizing visemes, that are the visual equivalent of phonemes-the smallest distinguishable sound unit in a spoken word. Viseme recognition has application in tasks such as lip synchronization, but acquiring and labeling a viseme dataset is complex and time-consuming. We tackle this problem by creating a large-scale synthetic 2D dataset based on realistic 3D facial models, automatically labelled. Then, we extract real viseme images from the GRID corpus-using audio data to locate phonemes via forced phonetic alignment and the registered video to extract the corresponding visemes-and evaluate the applicability of the synthetic dataset for recognizing real-world data." @default.
- W2897846591 created "2018-10-26" @default.
- W2897846591 creator A5053374622 @default.
- W2897846591 creator A5067109023 @default.
- W2897846591 creator A5080035422 @default.
- W2897846591 date "2018-07-01" @default.
- W2897846591 modified "2023-09-23" @default.
- W2897846591 title "Improving CNN-Based Viseme Recognition Using Synthetic Data" @default.
- W2897846591 cites W1556470778 @default.
- W2897846591 cites W2015143272 @default.
- W2897846591 cites W2060510034 @default.
- W2897846591 cites W2078711706 @default.
- W2897846591 cites W2098923380 @default.
- W2897846591 cites W2113814270 @default.
- W2897846591 cites W2142075667 @default.
- W2897846591 cites W2163973301 @default.
- W2897846591 cites W2243738093 @default.
- W2897846591 cites W2474638510 @default.
- W2897846591 cites W2531409750 @default.
- W2897846591 cites W2738406145 @default.
- W2897846591 cites W2741151796 @default.
- W2897846591 cites W2752520680 @default.
- W2897846591 cites W2891226622 @default.
- W2897846591 cites W2952746495 @default.
- W2897846591 doi "https://doi.org/10.1109/icme.2018.8486470" @default.
- W2897846591 hasPublicationYear "2018" @default.
- W2897846591 type Work @default.
- W2897846591 sameAs 2897846591 @default.
- W2897846591 citedByCount "3" @default.
- W2897846591 countsByYear W28978465912019 @default.
- W2897846591 countsByYear W28978465912020 @default.
- W2897846591 countsByYear W28978465912021 @default.
- W2897846591 crossrefType "proceedings-article" @default.
- W2897846591 hasAuthorship W2897846591A5053374622 @default.
- W2897846591 hasAuthorship W2897846591A5067109023 @default.
- W2897846591 hasAuthorship W2897846591A5080035422 @default.
- W2897846591 hasConcept C138885662 @default.
- W2897846591 hasConcept C153180895 @default.
- W2897846591 hasConcept C154945302 @default.
- W2897846591 hasConcept C155635449 @default.
- W2897846591 hasConcept C187691185 @default.
- W2897846591 hasConcept C2524010 @default.
- W2897846591 hasConcept C28490314 @default.
- W2897846591 hasConcept C33767174 @default.
- W2897846591 hasConcept C33923547 @default.
- W2897846591 hasConcept C41008148 @default.
- W2897846591 hasConcept C41895202 @default.
- W2897846591 hasConcept C61328038 @default.
- W2897846591 hasConcept C90805587 @default.
- W2897846591 hasConceptScore W2897846591C138885662 @default.
- W2897846591 hasConceptScore W2897846591C153180895 @default.
- W2897846591 hasConceptScore W2897846591C154945302 @default.
- W2897846591 hasConceptScore W2897846591C155635449 @default.
- W2897846591 hasConceptScore W2897846591C187691185 @default.
- W2897846591 hasConceptScore W2897846591C2524010 @default.
- W2897846591 hasConceptScore W2897846591C28490314 @default.
- W2897846591 hasConceptScore W2897846591C33767174 @default.
- W2897846591 hasConceptScore W2897846591C33923547 @default.
- W2897846591 hasConceptScore W2897846591C41008148 @default.
- W2897846591 hasConceptScore W2897846591C41895202 @default.
- W2897846591 hasConceptScore W2897846591C61328038 @default.
- W2897846591 hasConceptScore W2897846591C90805587 @default.
- W2897846591 hasLocation W28978465911 @default.
- W2897846591 hasOpenAccess W2897846591 @default.
- W2897846591 hasPrimaryLocation W28978465911 @default.
- W2897846591 hasRelatedWork W1510011591 @default.
- W2897846591 hasRelatedWork W2347555632 @default.
- W2897846591 hasRelatedWork W2360025963 @default.
- W2897846591 hasRelatedWork W2360785147 @default.
- W2897846591 hasRelatedWork W2362058810 @default.
- W2897846591 hasRelatedWork W2370299677 @default.
- W2897846591 hasRelatedWork W2542625678 @default.
- W2897846591 hasRelatedWork W2747840220 @default.
- W2897846591 hasRelatedWork W2936149813 @default.
- W2897846591 hasRelatedWork W2939420698 @default.
- W2897846591 isParatext "false" @default.
- W2897846591 isRetracted "false" @default.
- W2897846591 magId "2897846591" @default.
- W2897846591 workType "article" @default.