Fine-tuning a video encoder with self-distillation on cropped and shifted clips makes video-to-audio generation robust to partially visible Foley targets.
Mitigating and evaluating static bias of ac- tion representations in the background and the foreground
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation
Fine-tuning a video encoder with self-distillation on cropped and shifted clips makes video-to-audio generation robust to partially visible Foley targets.