Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization

TL;DR

This paper introduces a novel optical flow-based self-supervised method for localizing sound sources in videos, leveraging motion information to improve accuracy and achieve state-of-the-art results on standard datasets.

Contribution

It proposes using optical flow as a prior for sound source localization, significantly enhancing attention maps and localization performance without explicit annotations.

Findings

Achieves state-of-the-art results on Soundnet Flickr dataset.

Demonstrates that flow-based attention improves localization accuracy.

Validates effectiveness on VGG Sound Source dataset.

Abstract

Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual sound source localization. Finally, we benchmark our method on standard sound source localization datasets and achieve state-of-the-art performance on the Soundnet Flickr and VGG Sound Source datasets. Code: https://github.com/denfed/heartheflow.