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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-11
Main Authors: Fedorishin, Dennis, Deen Dayal Mohan, Jawade, Bhavin, Setlur, Srirangaraj, Govindaraju, Venu
Format: Article
Language:English
Subjects:
Annotations
Datasets
Optical flow (image analysis)
Sound localization
Sound sources
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422