Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
ECCV 2018 (Oral presentation)

Andrew Owens     Alexei A. Efros    
UC Berkeley

Paper   ·   Code!   ·   Slides   ·   Poster

     
Three applications of our model: action recognition, and on/off-screen audio-visual source separation.

Abstract

The thud of a bouncing ball, the onset of speech as lips open — when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals. In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation. We propose to learn such a representation in a self-supervised way, by training a neural network to predict whether video frames and audio are temporally aligned. We use this learned representation for three applications: (a) sound source localization, i.e. visualizing the source of sound in a video; (b) audio-visual action recognition; and (c) on/off-screen audio source separation, e.g. removing the off-screen translator's voice from a foreign official's speech.

Video


Concurrent work

Concurrently and independently from us, a number of groups have proposed closely related — and very interesting! — methods for source separation and sound localization. Here is a partial list: