In this paper, we propose a cyclic co-learning (CCoL) paradigm that can jointly learn sounding objectvisual grounding and audio-visual sound separation in a unified framework . We can leverage grounded object-sound relations to improve the results of sound separation . Meanwhile, benefiting from discriminativeinformation from separated sounds, we improve training example sampling forsounding object grounding . Extensive experiments show that the proposed framework outperforms the . compared recent approaches on both tasks,and they can benefit from each other with our cyclic .co-learning approach . The proposal is based on the fact that the . proposed framework outranks the compared approaches on . both tasks

Author(s) : Yapeng Tian, Di Hu, Chenliang Xu

Links : PDF - Abstract

Code :

Keywords : sound - grounding - object - cyclic - learning -

Leave a Reply

Your email address will not be published. Required fields are marked *