TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis

Résumé

In this paper, we present TMR, a simple yet effective approach for text to 3D human motion retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we tackle it as a standalone task. Our method extends the state-of-the-art text-to-motion synthesis model TEMOS, and incorporates a contrastive loss to better structure the cross-modal latent space. We show that maintaining the motion generation loss, along with the contrastive training, is crucial to obtain good performance. We introduce a benchmark for evaluation and provide an in-depth analysis by reporting results on several protocols. Our extensive experiments on the KIT-ML and HumanML3D datasets show that TMR outperforms the prior work by a significant margin, for example reducing the median rank from 54 to 19. Finally, we showcase the potential of our approach on moment retrieval. Our code and models are publicly available at https://mathis.petrovich.fr/tmr.
Fichier principal
Vignette du fichier
2305.00976.pdf (4.58 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04258206 , version 1 (25-10-2023)

Identifiants

Citer

Mathis Petrovich, Michael J. Black, Gül Varol. TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis. International Conference on Computer Vision, Oct 2023, Paris, France. ⟨hal-04258206⟩
170 Consultations
5 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More