Publications

Published in Computer Graphics Forum, 2024

This paper experiments with using Large-Language Model (LLM) features for gesture generation that are extracted from text using Llama2.

Recommended citation: J. Windle, I. Matthews, and S. Taylor, “Llanimation: Llama driven gesture animation,” Computer Graphics Forum, vol. n/a, no. n/a, e15167, DOI: https://doi.org/10.1111/cgf.15167. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.15167. https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.15167

Published in International Conference on Multimodal Interaction, 2023

This paper adapts the Transformer-XL architecture for dyadic gesture generation by adding a cross-attention module that integrates the interlocutor’s speech with that of the main-agent.

Recommended citation: Windle, J., Matthews, I., Milner, B., & Taylor, S. (2023, October). The UEA Digital Humans entry to the GENEA Challenge 2023. In Proceedings of the 25th International Conference on Multimodal Interaction (pp. 802-810). https://dl.acm.org/doi/abs/10.1145/3577190.3616116

Published in International Conference on Multimodal Interaction, 2022

This paper describes the UEA Digital Humans entry to the GENEA (Generation and Evaluation of Non-verbal Behaviour for Embodied Agents) challenge 2022

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

Published in Speech Communication, 2022

This paper reviews the motion symmetry of multiple speakers during dyadic conversation.

Recommended citation: Windle, J., Taylor, S., Greenwood, D., & Matthews, I. (2022). Arm motion symmetry in conversation. Speech Communication, 144, 75-88. https://www.sciencedirect.com/science/article/pii/S0167639322001054

Published in IVA '22: Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents, 2022

This paper investigates the effect of lateral mirroring as a means of data augmentation for 3D poses in multi-speaker, speech-to-motion modelling.

Recommended citation: Windle, J., Taylor, S., Greenwood, D., & Matthews, I. (2022, September). Pose augmentation: Mirror the right way. In Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents (pp. 1-3). https://dl.acm.org/doi/abs/10.1145/3514197.3549677

Published in Computers & Security, 2022

This paper builds upon the notion of keystroke dynamics (the analysis of typing behaviours) to infer an anonymous user’s name and predict their native language.

Recommended citation: Buckley, O., Hodges, D., Windle, J., & Earl, S. (2022). CLICKA: Collecting and leveraging identity cues with keystroke dynamics. Computers & Security, 120, 102780. https://www.sciencedirect.com/science/article/pii/S0167404822001754

Published in CVMP '21: European Conference on Visual Media Production, 2021

This paper introduces the Flow-VAE model for speech-driven gesture generation.

Recommended citation: Taylor, S., Windle, J., Greenwood, D., & Matthews, I. (2021, December). Speech-driven conversational agents using conditional flow-vaes. In Proceedings of the 18th ACM SIGGRAPH European Conference on Visual Media Production (pp. 1-9). https://dl.acm.org/doi/10.1145/3485441.3485647