2025

Evaluating the evaluators: Towards human-aligned metrics for missing markers reconstruction
Taras Kucherenko, Derek Peristy, Judith Butepage. ACM International Conference on Multimedia (ACM MM'25). 2025.

2023

The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings
Taras Kucherenko*, Rajmund Nagy*, Youngwoo Yoon*, Jieyeon Woo, Teodor Nikolov, Mihail Tsakov, and Gustav Eje Henter. ICMI'23. ACM.

2022

The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation
Youngwoo Yoon*, Pieter Wolfert*, Taras Kucherenko*, Carla Viegas, Teodor Nikolov, Mihail Tsakov, and Gustav Eje Henter. ICMI'22. ACM.

2021

A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
Rajmund Nagy*, Taras Kucherenko*, Birger Moell, Andre Pereira, Hedvig Kjellstrom, and Ulysses Bernardet. AAMAS 2021.
Paper Code
A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020
Taras Kucherenko*, Patrik Jonell*, Youngwoo Yoon*, Pieter Wolfert, and Gustav Eje Henter. International Conference on Intelligent User Interfaces. 2021.
Paper

2020

Best Paper Award
Gesticulator: A framework for semantically-aware speech-driven gesture generation
Taras Kucherenko, Patrik Jonell, Sanne van Waveren, Gustav Eje Henter, Simon Alexanderson, Iolanda Leite, and Hedvig Kjellstrom. ICMI'20.
Paper Code Project Page
Best Paper Award
Let's face it: Probabilistic multi-modal interlocutor-aware generation of facial gestures in dyadic settings
Patrik Jonell, Taras Kucherenko, Gustav Eje Henter, Jonas Beskow. IVA'20. 2020.
Paper
Best Paper Award Nominee
Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows
Simon Alexanderson, Gustav Eje Henter, Taras Kucherenko, and Jonas Beskow. EuroGraphics 2020.
Paper

2019

A general overview of my research
Analyzing input and output representations for speech-driven gesture generation
Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, and Hedvig Kjellstrom. IVA'19, Paris.
Paper Code
Demo: Speech-driven gesture generation applied to English dataset
Pre-trained Model

2018

A neural network approach to missing marker reconstruction in human motion capture
Taras Kucherenko, Jonas Beskow and Hedvig Kjellstrom. arXiv preprint, 2018.
Paper Code
Motion capture denoising demo
Using the same system as above for denoising applications.
Code