English

Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

Computer Vision and Pattern Recognition 2018-10-10 v2 Sound Audio and Speech Processing

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. Code, models, and video results are available on our webpage: http://andrewowens.com/multisensory

Keywords

Cite

@article{arxiv.1804.03641,
  title  = {Audio-Visual Scene Analysis with Self-Supervised Multisensory Features},
  author = {Andrew Owens and Alexei A. Efros},
  journal= {arXiv preprint arXiv:1804.03641},
  year   = {2018}
}
R2 v1 2026-06-23T01:19:37.991Z