@inproceedings{mo-etal-2025-improving,
title = "Improving Sign Language Understanding with a Multi-Stream Masked Autoencoder Trained on {ASL} Videos",
author = "Mo, Junwen and
Vo, MinhDuc and
Nakayama, Hideki",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.66/",
pages = "1202--1218",
ISBN = "979-8-89176-298-5",
abstract = "Sign language understanding remains a significant challenge, particularly for low-resource sign languages with limited annotated data. Motivated by the success of large-scale pretraining in deep learning, we propose Multi-Stream Masked Autoencoder (MS-MAE) {---} a simple yet effective framework for learning sign language representations from skeleton-based video data. We pretrained a model with MS-MAE on the YouTube-ASL dataset, and then adapted it to multiple downstream tasks across different sign languages. Experimental results show that MS-MAE achieves competitive or superior performance on a range of isolated sign language recognition benchmarks and gloss-free sign language translation tasks across several sign languages. These findings highlight the potential of leveraging large-scale, high-resource sign language data to boost performance in low-resource sign language scenarios. Additionally, visualization of the model{'}s attention maps reveals its ability to cluster adjacent pose sequences within a sentence, some of which align with individual signs, offering insights into the mechanisms underlying successful transfer learning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mo-etal-2025-improving">
<titleInfo>
<title>Improving Sign Language Understanding with a Multi-Stream Masked Autoencoder Trained on ASL Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junwen</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">MinhDuc</namePart>
<namePart type="family">Vo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Sign language understanding remains a significant challenge, particularly for low-resource sign languages with limited annotated data. Motivated by the success of large-scale pretraining in deep learning, we propose Multi-Stream Masked Autoencoder (MS-MAE) — a simple yet effective framework for learning sign language representations from skeleton-based video data. We pretrained a model with MS-MAE on the YouTube-ASL dataset, and then adapted it to multiple downstream tasks across different sign languages. Experimental results show that MS-MAE achieves competitive or superior performance on a range of isolated sign language recognition benchmarks and gloss-free sign language translation tasks across several sign languages. These findings highlight the potential of leveraging large-scale, high-resource sign language data to boost performance in low-resource sign language scenarios. Additionally, visualization of the model’s attention maps reveals its ability to cluster adjacent pose sequences within a sentence, some of which align with individual signs, offering insights into the mechanisms underlying successful transfer learning.</abstract>
<identifier type="citekey">mo-etal-2025-improving</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.66/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1202</start>
<end>1218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Sign Language Understanding with a Multi-Stream Masked Autoencoder Trained on ASL Videos
%A Mo, Junwen
%A Vo, MinhDuc
%A Nakayama, Hideki
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F mo-etal-2025-improving
%X Sign language understanding remains a significant challenge, particularly for low-resource sign languages with limited annotated data. Motivated by the success of large-scale pretraining in deep learning, we propose Multi-Stream Masked Autoencoder (MS-MAE) — a simple yet effective framework for learning sign language representations from skeleton-based video data. We pretrained a model with MS-MAE on the YouTube-ASL dataset, and then adapted it to multiple downstream tasks across different sign languages. Experimental results show that MS-MAE achieves competitive or superior performance on a range of isolated sign language recognition benchmarks and gloss-free sign language translation tasks across several sign languages. These findings highlight the potential of leveraging large-scale, high-resource sign language data to boost performance in low-resource sign language scenarios. Additionally, visualization of the model’s attention maps reveals its ability to cluster adjacent pose sequences within a sentence, some of which align with individual signs, offering insights into the mechanisms underlying successful transfer learning.
%U https://aclanthology.org/2025.ijcnlp-long.66/
%P 1202-1218
Markdown (Informal)
[Improving Sign Language Understanding with a Multi-Stream Masked Autoencoder Trained on ASL Videos](https://aclanthology.org/2025.ijcnlp-long.66/) (Mo et al., IJCNLP-AACL 2025)
ACL