LG-CAV-MAE trains a tri-modal audio-visual-text model on CLAP-filtered auto-generated captions and beats existing audio-visual masked autoencoders on retrieval and classification.
We also propose to automatically gener- ate audio-visual-text triplets from unlabeled videos, which are subsequently used for training LG-CA V-MAE
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
-
Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
LG-CAV-MAE trains a tri-modal audio-visual-text model on CLAP-filtered auto-generated captions and beats existing audio-visual masked autoencoders on retrieval and classification.