Pith. sign in

REVIEW 1 cited by

Siamese Vision Transformers are Scalable Audio-visual 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

arxiv 2403.19638 v1 pith:ZLHXYK6L submitted 2024-03-28 cs.CV cs.SDeess.AS

classification cs.CVcs.SDeess.AS
keywords audio-visualaudioavsiambackbonemethodsmodelscalableshared
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual pretraining. Our framework uses a single shared vision transformer backbone to process audio and visual inputs, improving its parameter efficiency, reducing the GPU memory footprint, and allowing us to scale our method to larger datasets and model sizes. We pretrain our model using a contrastive audio-visual matching objective with a multi-ratio random masking scheme, which enables our model to process larger audio-visual instance batches, helpful for contrastive learning. Unlike prior audio-visual methods, our method can robustly handle audio, visual, and audio-visual inputs with a single shared ViT backbone. Furthermore, despite using the shared backbone for both modalities, AVSiam achieves competitive or even better results than prior methods on AudioSet and VGGSound for audio-visual classification and retrieval. Our code is available at https://github.com/GenjiB/AVSiam

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Adaptive Perception for Unified Visual Multi-modal Object Tracking

    cs.CV 2025-02 conditional novelty 5.0 of 10

    APTrack shows that a single unified multi-modal tracker using equal modality modeling and learnable token interaction can beat both unified and task-specific trackers on RGB-T, RGB-D, and RGB-E benchmarks.

Pith tools