English

Understanding Co-speech Gestures in-the-wild

Computer Vision and Pattern Recognition 2025-08-22 v2

Abstract

Co-speech gestures play a vital role in non-verbal communication. In this paper, we introduce a new framework for co-speech gesture understanding in the wild. Specifically, we propose three new tasks and benchmarks to evaluate a model's capability to comprehend gesture-speech-text associations: (i) gesture based retrieval, (ii) gesture word spotting, and (iii) active speaker detection using gestures. We present a new approach that learns a tri-modal video-gesture-speech-text representation to solve these tasks. By leveraging a combination of global phrase contrastive loss and local gesture-word coupling loss, we demonstrate that a strong gesture representation can be learned in a weakly supervised manner from videos in the wild. Our learned representations outperform previous methods, including large vision-language models (VLMs). Further analysis reveals that speech and text modalities capture distinct gesture related signals, underscoring the advantages of learning a shared tri-modal embedding space. The dataset, model, and code are available at: https://www.robots.ox.ac.uk/~vgg/research/jegal.

Keywords

Cite

@article{arxiv.2503.22668,
  title  = {Understanding Co-speech Gestures in-the-wild},
  author = {Sindhu B Hegde and K R Prajwal and Taein Kwon and Andrew Zisserman},
  journal= {arXiv preprint arXiv:2503.22668},
  year   = {2025}
}

Comments

Main paper - 11 pages, 4 figures, Supplementary - 6 pages, 6 figures

R2 v1 2026-06-28T22:38:23.246Z