Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Prompting with Sign Parameters for Low-resource Sign Language Instruction Generation

Domaine:

natural language processingeducation

Type de record:

paperdataset
Créateur:
TarIshMunHas
Hôte:avatar
Sign Language (SL) enables two-way communication for the deaf and hard-of-hearing community, yet many sign languages remain under-resourced in the AI space. Sign Language Instruction Generation (SLIG) produces step-by-step textual instructions that enable non-SL users to imitate and learn SL gestures, promoting two-way interaction. We introduce BdSLIG, the first Bengali SLIG dataset, used to evaluate Vision Language Models (VLMs) (i) on under-resourced SLIG tasks, and (ii) on long-tail visual concepts, as Bengali SL is unlikely to appear in the VLM pre-training data. To enhance zero-shot performance, we introduce Sign Parameter-Infused (SPI) prompting, which integrates standard SL parameters, like hand shape, motion, and orientation, directly into the textual prompts. Subsuming standard sign parameters into the prompt makes the instructions more structured and reproducible than free-form natural text from vanilla prompting. We envision that our work would promote inclusivity and advancement in SL learning systems for the under-resourced communities. CV4A11y@ICCV 2025

Visit

arxiv.org

Tasks

computer visionsign-language to text

Tags

Human-Computer InteractionComputer Vision and Pattern Recognition

Similaires

Towards the extraction of robust sign embeddings for low resource sign language recognitionSign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign LanguageSign-to-Speech Model for Sign Language Understanding: A Case Study of Nigerian Sign LanguageAn end-to-end framework for translation of American sign language to low-resource languages in NigeriaGenetic relatedness of Tunisian Sign Language and French Sign Languageamharic-speach-2-sign-language/speach-2-sign

Towards the extraction of robust sign embeddings for low resource sign language recognition

Isolated Sign Language Recognition (SLR) has mostly been applied on datasets containing signs execut

Sign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign Language

Our dataset is a novel dataset for the Nigerian Sign Language comprising of 5000 images of 137 sign words/phrases including the alphabet letters. Data collectors of 20+ individuals comprising of a TV sign language broadcaster and students and teachers from 2 specia

Sign-to-Speech Model for Sign Language Understanding: A Case Study of Nigerian Sign Language

Through this paper, we seek to reduce the communication barrier between the hearing-impaired community and the larger society who are usually not familiar with sign language in the sub-Saharan region of Africa with the largest occurrences of hearing disability case

An end-to-end framework for translation of American sign language to low-resource languages in Nigeria

Genetic relatedness of Tunisian Sign Language and French Sign Language

This article constitutes the first cognate study aiming at the verification of the genetic link betw

amharic-speach-2-sign-language/speach-2-sign

Amharic voice to sign language translator # speach-2-sign Amharic voice to sign language translator