People recognition using gamified ambiguous feedback

Abstract

We present a semi-supervised approach to recognize faces or people while incorporating crowd-sourced and gamified feedback to iteratively improve recognition accuracy. Unlike traditional approaches which are often limited to explicit feedback, we model ambiguous feedback information that we implicitly gather through a crowd that plays a game. We devise a graph-based recognition approach that incorporates such ambiguous feedback to jointly recognize people across an entire dataset. Multiple experiments demonstrate the effectiveness of our gamified feedback approach.