Q-BridgeNet: A quantization network for cross-lingual sign language translation
Author Identifier (ORCID)
Abstract
Most sign language translation (SLT) methods focus on isolated native sign–spoken pairs (e.g., American Sign Language–English). Extending language-specific SLT models to multilingual translation would improve accessibility by enabling communication across diverse sign and spoken language communities. However, existing multilingual SLT approaches still struggle to learn a unified model that minimizes cross-lingual conflicts while capturing shared cross-lingual semantics and preserving language-specific variations across different sign languages. Therefore, we propose Q-BridgeNet, a unified framework for multilingual SLT that jointly mitigates cross-lingual conflicts across both the sign language and spoken language sides. On the sign language side, Q-BridgeNet learns discrete Q-units via adaptive segmentation and residual vector quantization: a shared base codebook provides language-agnostic semantic primitives, while language-specific residual codebooks refine heterogeneous signing semantics. On the spoken language side, a multilingual LLM is fine-tuned to operate in the Q-unit space, leveraging cross-lingual priors to enable a unified SLT model. Experiments on PHOENIX14T, How2Sign, and CSL-Daily show that Q-BridgeNet effectively mitigates cross-lingual conflicts, achieving state-of-the-art performance on native sign–spoken pairs while also demonstrating strong generalization to non-native pairs. Our source code is publicly available at: https://github.com/FengLiQ/Q-BridgeNet.
Keywords
multilingual modeling, representation learning, sign language translation
Document Type
Conference Proceeding
Date of Publication
1-1-2026
E-ISSN
16113349
ISSN
03029743
Volume
17008 LNCS
Publication Title
Computer Vision – ECCV 2026
Publisher
Springer
School
School of Science
Funding Information
This research was supported by the Australian Research Council (ARC) under Project LP230100294 and the Edith Cowan University (ECU) Early-Mid Career Researcher (EMCR) Grant Scheme. Dr. Anusha Withana is the recipient of a Future Fellowship (FT250100813) funded by ARC.
Funding received from the Australian Research Council (ARC)
LP230100294, FT250100813
ISBN
[9783032370259]
Copyright
subscription content
First Page
355
Last Page
372
Recommended Citation
Feng, L., Wang, L., Liu, X., Withana, A., Yong, K.-T., Kong, D., Wang, Z., & Hu, K. (2026). Q-BridgeNet: A quantization network for cross-lingual sign language translation. In P. Favaro, Z. Kukelova, A. Maki, A. Rohrbach, K. Schindler, & F. Tombari (Eds.), Computer vision – ECCV 2026 (pp. 355–372). Springer. https://doi.org/10.1007/978-3-032-37026-6_20