no code implementations • EACL (HCINLP) 2021 • Imke van Heerden, Anil Bas
This paper proposes a generative language model called AfriKI.
1 code implementation • 16 Feb 2021 • M. Onat Topal, Anil Bas, Imke van Heerden
Recent years have seen a proliferation of attention mechanisms and the rise of Transformers in Natural Language Generation (NLG).
no code implementations • 7 Apr 2018 • Anil Bas, William A. P. Smith
In this configuration, our model learns an active appearance model and a means to fit the model from scratch with no supervision at all, even identity labels.
1 code implementation • 23 Aug 2017 • Anil Bas, Patrik Huber, William A. P. Smith, Muhammad Awais, Josef Kittler
In this paper, we show how a 3D Morphable Model (i. e. a statistical model of the 3D shape of a class of objects such as faces) can be used to spatially transform input data as a module (a 3DMM-STN) within a convolutional neural network.
1 code implementation • 22 Aug 2017 • Anil Bas, William A. P. Smith
We show that this is not the case and that geometric information is an ambiguous cue.
1 code implementation • 2 Feb 2016 • Anil Bas, William A. P. Smith, Timo Bolkart, Stefanie Wuhrer
We propose a fully automatic method for fitting a 3D morphable model to single face images in arbitrary pose and lighting.