Entropy-aware gating and shuffled audio-video training pairs improve robustness to audiovisual mismatch in video-guided audio captioning.
Moreover, our system achieves an approximately 6x im- provement in inference speed compared to the baseline while still maintaining competitive accuracy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
Entropy-aware gating and shuffled audio-video training pairs improve robustness to audiovisual mismatch in video-guided audio captioning.