MAViT Multimodal active learning for video talking head generation

Das, Gyanedra2024-11-132024-11-132024-05http://hdl.handle.net/123456789/4106enArtificial IntelligenceMultimodal semantics aware sequential entropySophisticated iterative processDISTDS1586AMTMAViT Multimodal active learning for video talking head generationThesis