"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos."

Hao-Wen Dong et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2212.07065

access: open

type: Informal or Other Publication

metadata version: 2023-01-02

a service of  Schloss Dagstuhl - Leibniz Center for Informatics