CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
By: Edson Araujo , Andrew Rouditchenko , Yuan Gong and more
Potential Business Impact:
Lets computers understand sounds and pictures together.
Recent advances in audio-visual learning have shown promising results in learning representations across modalities. However, most approaches rely on global audio representations that fail to capture fine-grained temporal correspondences with visual frames. Additionally, existing methods often struggle with conflicting optimization objectives when trying to jointly learn reconstruction and cross-modal alignment. In this work, we propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE framework for self-supervised audio-visual learning. We address three key challenges: First, we tackle the granularity mismatch between modalities by treating audio as a temporal sequence aligned with video frames, rather than using global representations. Second, we resolve conflicting optimization goals by separating contrastive and reconstruction objectives through dedicated global tokens. Third, we improve spatial localization by introducing learnable register tokens that reduce semantic load on patch tokens. We evaluate the proposed approach on AudioSet, VGG Sound, and the ADE20K Sound dataset on zero-shot retrieval, classification and localization tasks demonstrating state-of-the-art performance and outperforming more complex architectures.
Similar Papers
SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation
Artificial Intelligence
Makes videos of people talking match sound.
Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice
CV and Pattern Recognition
Helps computers understand people talking and acting.
LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders
CV and Pattern Recognition
Helps computers understand long videos better.