Skip to yearly menu bar Skip to main content


Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos

Sagnik Majumder · Ziad Al-Halah · Kristen Grauman

Arch 4A-E Poster #280
[ ]
Fri 21 Jun 5 p.m. PDT — 6:30 p.m. PDT


We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio through the synergy of audio and vision, thereby learning useful spatial relationships between the two modalities. We use our pretrained features to tackle two downstream video tasks requiring spatial understanding in social scenarios: active speaker detection and spatial audio denoising. Through extensive experiments, we show that our features are generic enough to improve over multiple state-of-the-art baselines on both tasks on two challenging egocentric video datasets that offer binaural audio, EgoCom and EasyCom.

Live content is unavailable. Log in and register to view live content