Preprint
Oct 2026
Semantic-Critical Regions for Video-to-Audio Generation
In real-world videos, sound events are often associated with localized and fine-grained visual cues, such as object motion, object-part dynamics, contact events, and interactions between objects. Existing video-to-audio (V2A) methods employ implicit conditioning based on global visual representations or explicit contro...
Yu-Ming Fang, Wei Guo, Zhuo-Nan Liang et al.
· 0 citations