UEA Digital Humans entry to the GENEA Challenge 2022
Published in International Conference on Multimodal Interaction, 2022
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.
Recommended citation: Windle, J., Greenwood, D., & Taylor, S. (2022, November). UEA Digital Humans entry to the GENEA Challenge 2022. In Proceedings of the 2022 International Conference on Multimodal Interaction (pp. 771-777). https://dl.acm.org/doi/abs/10.1145/3536221.3558065