Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Siyu, Li, Yunan, Xin, Wentian, Chen, Huizhou, Liu, Xujie, Liu, Kang, Miao, Qiguang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912495836332032
author Liang, Siyu
Li, Yunan
Xin, Wentian
Chen, Huizhou
Liu, Xujie
Liu, Kang
Miao, Qiguang
author_facet Liang, Siyu
Li, Yunan
Xin, Wentian
Chen, Huizhou
Liu, Xujie
Liu, Kang
Miao, Qiguang
contents Sign language recognition (SLR) faces fundamental challenges in creating accurate annotations due to the inherent complexity of simultaneous manual and non-manual signals. To the best of our knowledge, this is the first work to integrate generative large language models (LLMs) into SLR tasks. We propose a novel Generative Sign-description Prompts Multi-positive Contrastive learning (GSP-MC) method that leverages retrieval-augmented generation (RAG) with domain-specific LLMs, incorporating multi-step prompt engineering and expert-validated sign language corpora to produce precise multipart descriptions. The GSP-MC method also employs a dual-encoder architecture to bidirectionally align hierarchical skeleton features with multiple text descriptions (global, synonym, and part level) through probabilistic matching. Our approach combines global and part-level losses, optimizing KL divergence to ensure robust alignment across all relevant text-skeleton pairs while capturing both sign-level semantics and detailed part dynamics. Experiments demonstrate state-of-the-art performance against existing methods on the Chinese SLR500 (reaching 97.1%) and Turkish AUTSL datasets (97.07% accuracy). The method's cross-lingual effectiveness highlight its potential for developing inclusive communication technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02304
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition
Liang, Siyu
Li, Yunan
Xin, Wentian
Chen, Huizhou
Liu, Xujie
Liu, Kang
Miao, Qiguang
Computation and Language
Computer Vision and Pattern Recognition
Sign language recognition (SLR) faces fundamental challenges in creating accurate annotations due to the inherent complexity of simultaneous manual and non-manual signals. To the best of our knowledge, this is the first work to integrate generative large language models (LLMs) into SLR tasks. We propose a novel Generative Sign-description Prompts Multi-positive Contrastive learning (GSP-MC) method that leverages retrieval-augmented generation (RAG) with domain-specific LLMs, incorporating multi-step prompt engineering and expert-validated sign language corpora to produce precise multipart descriptions. The GSP-MC method also employs a dual-encoder architecture to bidirectionally align hierarchical skeleton features with multiple text descriptions (global, synonym, and part level) through probabilistic matching. Our approach combines global and part-level losses, optimizing KL divergence to ensure robust alignment across all relevant text-skeleton pairs while capturing both sign-level semantics and detailed part dynamics. Experiments demonstrate state-of-the-art performance against existing methods on the Chinese SLR500 (reaching 97.1%) and Turkish AUTSL datasets (97.07% accuracy). The method's cross-lingual effectiveness highlight its potential for developing inclusive communication technologies.
title Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.02304