Motion2Language, Unsupervised Learning of Synchronized Semantic Motion Segmentation - IMT Mines Alès Accéder directement au contenu
Article Dans Une Revue Neural Computing and Applications Année : 2024

Motion2Language, Unsupervised Learning of Synchronized Semantic Motion Segmentation

Karim Radouane
Julien Lagarde
Sylvie Ranwez

Résumé

In this paper, we investigate building a sequence to sequence architecture for motion-to-language translation and synchronization. The aim is to translate motion capture inputs into English natural-language descriptions, such that the descriptions are generated synchronously with the actions performed, enabling semantic segmentation as a byproduct, but without requiring synchronized training data. We propose a new recurrent formulation of local attention that is suited for synchronous/live text generation, as well as an improved motion encoder architecture better suited to smaller data and for synchronous generation. We evaluate both contributions in individual experiments, using the standard BLEU4 metric, as well as a simple semantic equivalence measure, on the KIT motion-language dataset. In a follow-up experiment, we assess the quality of the synchronization of generated text in our proposed approaches through multiple evaluation metrics. We find that both contributions to the attention mechanism and the encoder architecture additively improve the quality of generated text (BLEU and semantic equivalence), but also of synchronization.
Fichier principal
Vignette du fichier
motion2language.pdf (7.03 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04251173 , version 1 (20-10-2023)

Identifiants

Citer

Karim Radouane, Andon Tchechmedjiev, Julien Lagarde, Sylvie Ranwez. Motion2Language, Unsupervised Learning of Synchronized Semantic Motion Segmentation. Neural Computing and Applications, 2024, 36, p. 4401-4420. ⟨10.1007/s00521-023-09227-z⟩. ⟨hal-04251173⟩
95 Consultations
30 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More