"SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data ..."

William Havard, Laurent Besacier, Olivier Rosec (2017)

Details and statistics

DOI:

access: open

type: Informal or Other Publication

metadata version: 2018-08-13

a service of  Schloss Dagstuhl - Leibniz Center for Informatics