Mini-3DCvT: a lightweight lip-reading method based on 3D convolution visual transformer
Huijuan Wang, Boyan Cui, Quanbo Yuan, Gangqiang Pu, Xueli Liu, Jie Zhu
Topics & Concepts
Computer scienceTransformerReading (process)Convolution (computer science)Computer graphics (images)Artificial intelligenceLinguisticsEngineeringElectrical engineeringPhilosophyVoltageArtificial neural networkSpeech and Audio ProcessingFace recognition and analysisHand Gesture Recognition Systems