Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306651738> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4306651738 endingPage "10484" @default.
- W4306651738 startingPage "10484" @default.
- W4306651738 abstract "Lipreading refers to the task of decoding the text content of a speaker based on visual information about the movement of the speaker’s lips. With the development of deep learning in recent years, lipreading has attracted extensive research. However, the deep learning method requires a lot of computing resources, which is not conducive to the migration of the system to edge devices. Inspired by the work of Spiking Neural Networks (SNNs) in recognizing human actions and gestures, we propose a lipreading system based on SNNs. Specifically, we construct the front-end feature extractor of the system using Liquid State Machine (LSM). On the other hand, a heuristic algorithm is used to select appropriate parameters for the classifier in the backend. On small-scale lipreading datasets, our recognition accuracy achieves good results. We claim that our network performs better in terms of accuracy and ratio of learned parameters compared to other networks, and has superior advantages in terms of network complexity and training cost. On the AVLetters dataset, our model achieves a 5% improvement in accuracy over traditional methods and a 90% reduction in parameters over the state-of-the-art." @default.
- W4306651738 created "2022-10-18" @default.
- W4306651738 creator A5009241973 @default.
- W4306651738 creator A5027095108 @default.
- W4306651738 creator A5073216396 @default.
- W4306651738 creator A5089096536 @default.
- W4306651738 date "2022-10-17" @default.
- W4306651738 modified "2023-10-17" @default.
- W4306651738 title "Lipreading Using Liquid State Machine with STDP-Tuning" @default.
- W4306651738 cites W101771737 @default.
- W4306651738 cites W1962124124 @default.
- W4306651738 cites W1968263568 @default.
- W4306651738 cites W2040666687 @default.
- W4306651738 cites W2057755457 @default.
- W4306651738 cites W2063810326 @default.
- W4306651738 cites W2076015009 @default.
- W4306651738 cites W2096391593 @default.
- W4306651738 cites W2103179919 @default.
- W4306651738 cites W2113814270 @default.
- W4306651738 cites W2126105956 @default.
- W4306651738 cites W2127141656 @default.
- W4306651738 cites W2130334496 @default.
- W4306651738 cites W2136155248 @default.
- W4306651738 cites W2153564253 @default.
- W4306651738 cites W2404704342 @default.
- W4306651738 cites W2609629010 @default.
- W4306651738 cites W2620831983 @default.
- W4306651738 cites W2788722888 @default.
- W4306651738 cites W2888634444 @default.
- W4306651738 cites W2890952074 @default.
- W4306651738 cites W2943455019 @default.
- W4306651738 cites W2969331319 @default.
- W4306651738 cites W3003241499 @default.
- W4306651738 cites W3016011581 @default.
- W4306651738 cites W3136670598 @default.
- W4306651738 doi "https://doi.org/10.3390/app122010484" @default.
- W4306651738 hasPublicationYear "2022" @default.
- W4306651738 type Work @default.
- W4306651738 citedByCount "0" @default.
- W4306651738 crossrefType "journal-article" @default.
- W4306651738 hasAuthorship W4306651738A5009241973 @default.
- W4306651738 hasAuthorship W4306651738A5027095108 @default.
- W4306651738 hasAuthorship W4306651738A5073216396 @default.
- W4306651738 hasAuthorship W4306651738A5089096536 @default.
- W4306651738 hasBestOaLocation W43066517381 @default.
- W4306651738 hasConcept C117978034 @default.
- W4306651738 hasConcept C127413603 @default.
- W4306651738 hasConcept C153180895 @default.
- W4306651738 hasConcept C154945302 @default.
- W4306651738 hasConcept C21880701 @default.
- W4306651738 hasConcept C28490314 @default.
- W4306651738 hasConcept C41008148 @default.
- W4306651738 hasConcept C95623464 @default.
- W4306651738 hasConceptScore W4306651738C117978034 @default.
- W4306651738 hasConceptScore W4306651738C127413603 @default.
- W4306651738 hasConceptScore W4306651738C153180895 @default.
- W4306651738 hasConceptScore W4306651738C154945302 @default.
- W4306651738 hasConceptScore W4306651738C21880701 @default.
- W4306651738 hasConceptScore W4306651738C28490314 @default.
- W4306651738 hasConceptScore W4306651738C41008148 @default.
- W4306651738 hasConceptScore W4306651738C95623464 @default.
- W4306651738 hasFunder F4320321001 @default.
- W4306651738 hasIssue "20" @default.
- W4306651738 hasLocation W43066517381 @default.
- W4306651738 hasLocation W43066517382 @default.
- W4306651738 hasOpenAccess W4306651738 @default.
- W4306651738 hasPrimaryLocation W43066517381 @default.
- W4306651738 hasRelatedWork W1979583797 @default.
- W4306651738 hasRelatedWork W2033914206 @default.
- W4306651738 hasRelatedWork W2042327336 @default.
- W4306651738 hasRelatedWork W2049864679 @default.
- W4306651738 hasRelatedWork W2114169842 @default.
- W4306651738 hasRelatedWork W2535808783 @default.
- W4306651738 hasRelatedWork W2945706271 @default.
- W4306651738 hasRelatedWork W2953302367 @default.
- W4306651738 hasRelatedWork W3183408266 @default.
- W4306651738 hasRelatedWork W4387435415 @default.
- W4306651738 hasVolume "12" @default.
- W4306651738 isParatext "false" @default.
- W4306651738 isRetracted "false" @default.
- W4306651738 workType "article" @default.