Search Publication
Export 3 results:
Author Title [ Type] Year Filters: Author is Roldán, Francisco [Clear All Filters]
Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks. In ICASSP. Brighton, UK: IEEE; 2019. (4.42 MB)
. Speech-conditioned Face Generation with Deep Adversarial Networks. . 2018. (1.79 MB)
. Visual Question Answering 2.0. . 2017. (2.59 MB)
.