← Search

Peiwu Qin

1 accepted papers

2025

TAGMO: Temporal Control Audio Generation for Multiple Visual Objects Without Training

ICASSP 2025accepted

With the great popularity of Sora, video-based audio generation has become indispensable. While numerous video-to-audio generation models have emerged, they frequently face difficulties including semantic incompatibilities and synchronization problems, especially in situations with multiple objects.…

Cited by 0SourceScholar