There are 0 repository under visual-audio topic.
A Music Player that can show audio waveform
Database of "Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model", ECCV 2020
EchoSight is a tool that helps visually impaired individuals by audibly describing images taken with a Raspberry Pi Camera or inputted via image path or URL across different operating systems.
Code for "Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model", ECCV 2020
Source code for "Visually aligned sound generation via sound-producing motion parsing" (Published at Neurocomputing)