REVIEW 3 cited by
MAViL: Masked Audio-Video Learners
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks.
Forward citations
Cited by 3 Pith papers
-
Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
Passive scene audio, especially direction-of-arrival cues, improves relative camera pose estimation when combined with vision in real-world videos.
-
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Dictionary learning with ICFL and control-data whitening extracts sparse features from microscopy foundation models that correlate with cell types and genetic perturbations.
-
A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning
A review that categorizes deep audio-visual correlation learning methods by architectures, objective functions, datasets, and evaluation metrics, and points to missing standardized benchmarks.
Discussion (0). Continue with ORCID to comment.