UEA Digital Humans entry to the GENEA Challenge 2022

Jonathan Windle, David Greenwood, Sarah Taylor

Abstract: This paper describes our entry to the GENEA (Generation and Evaluation of Non-verbal Behaviour for Embodied Agents) challenge 2022. The challenge aims to further the scientific knowledge using a large-scale, joint subjective evaluation of many gesture generation systems. We present two models to the challenge. A Bi-Directional LSTM for the full-body tier and a BDLSTM multi-decoder to produce body-section specific experts. We develop a loss function using both rotations and positions for training our models. We also introduce PASE+ features to the task of pose prediction, along with FastText word embeddings. Our models performed competitively regarding human likeness, and our multiple decoder system performed in the top two submissions for appropriateness of gesture.