IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022, New Orleans, USA

 

Our contribution to the

 

VizWiz Grand Challenge: Describing Images and Videos Taken by Blind People

 

Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model

 

Fabian Deuser, Konrad Habel, Philipp J. RöschTwitter_Social_Icon_Circle_Color.png, Norbert Oswald
University of the Bundeswehr Munich

 

[VizWiz], [arXiv], [Video], [Demo]