SignAvatar: Sign Language 3D Motion Reconstruction and Generation

Achieving expressive 3D motion reconstruction and automatic generation for isolated sign words can be challenging, due to the lack of real-world 3D sign-word data, the complex nuances of signing motions, and the cross-modal understanding of sign language semantics. To address these challenges, we in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Conference and Workshops on Automatic Face and Gesture Recognition : FG S. 1 - 10
Hauptverfasser: Dong, Lu, Chaudhary, Lipisha, Xu, Fei, Wang, Xiao, Lary, Mason, Nwogu, Ifeoma
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 27.05.2024
Schlagworte:
Assistive technologies
Codes
Face recognition
Semantics
Sign language
Three-dimensional displays
Transformers
ISSN:2770-8330
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Achieving expressive 3D motion reconstruction and automatic generation for isolated sign words can be challenging, due to the lack of real-world 3D sign-word data, the complex nuances of signing motions, and the cross-modal understanding of sign language semantics. To address these challenges, we introduce SignAvatar, a framework capable of both word-level sign language reconstruction and generation. SignAvatar employs a transformer-based conditional variational autoencoder architecture, effectively establishing relationships across different semantic modalities. Additionally, this approach incorporates a curriculum learning strategy to enhance the model's robustness and generalization, resulting in more realistic motions. Furthermore, we contribute the ASL3DWord dataset, composed of 3D joint rotation data for the body, hands, and face, for unique sign words. We demonstrate the effectiveness of SignAvatar through extensive experiments, showcasing its superior reconstruction and automatic generation capabilities. The code and dataset are available on the project page1.
ISSN:2770-8330
DOI:10.1109/FG59268.2024.10581934