CVPR Daily - Tuesday

26 DAILY CVPR Tuesday Posters… ☺ Lucas Ventura, a PhD student in the IMAGINE computer vision team at Ecole des Ponts ParisTech (ENPC) and Inria (Paris), supervised by Cordelia Schmid and Gül Varol, presented his poster about text-to-video retrieval without access to manually-labeled videos. The model is trained using automatic frame captions, which constitute free labels for supervision. Work was presented at the Workshop on Learning with Limited Labelled Data for Image and Video Understanding.