@inproceedings{nam-takahashi-2026-care,
title = "{CARE}: A Coverage-Aware Retrieval Ensemble for Isolated Sign Language Recognition",
author = "Nam, Nguyen Tu and
Takahashi, Hiroki",
editor = "Singh, Sanjeet and
Joshi, Abhinav and
Dattatreya, Pokala and
Artiaga, Keren and
Pujara, Khushi Jaydeep and
{\v{Z}}elezn{\'y}, Tom{\'a}{\v{s}} and
Gruber, Ivan and
Honz{\'i}k, Jakub and
Kamila, Sabyasachi and
Quiroga, Facundo Manuel and
Hr{\'u}z, Marek and
Hasanuzzaman, Mohammed and
Modi, Ashutosh",
booktitle = "Proceedings of the Second Workshop on Sign Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wslp-1.14/",
pages = "141--146",
ISBN = "979-8-89176-488-0",
abstract = "Isolated sign language recognition is commonly formulated as supervised classification, but this formulation is challenging when nearly every target gloss has only one labeled video. We study the Isolated Sign Language Recognition track of the WSLP 2026 Shared Task on Indian Sign Language Processing, a predominantly one-shot target setting with 4,398 training videos spanning 4,361 glosses, over 99{\%} of which are singletons. We introduce CARE, a Coverage-Aware Retrieval Ensemble that augments a complete local visual dictionary with a CISLR reference bank covering a subset of the target vocabulary. A frozen Video-Swin encoder ranks all target labels locally, while frozen I3D and SignRep encoders provide external retrieval evidence for lexically matched labels. CARE estimates orthogonal Procrustes mappings from shared-class centroids, retains both raw and aligned representation geometries, and preserves external videos as individual nearest-neighbor references. Query-wise score standardization and a deterministic coverage mask restrict external evidence to supported labels. The method requires neither target-specific backbone fine-tuning nor a large-vocabulary classification head. CARE obtains 74.31{\%}/76.15{\%}/76.15{\%} Top-1/5/10 accuracy on the WSLP 2026 validation split and 65.59{\%}/67.11{\%}/68.25{\%} on the official test split. The 8.72{\%} Top-1 gap warrants caution when interpreting performance on the small 109-query validation split used for model selection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nam-takahashi-2026-care">
<titleInfo>
<title>CARE: A Coverage-Aware Retrieval Ensemble for Isolated Sign Language Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="given">Tu</namePart>
<namePart type="family">Nam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Sign Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanjeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pokala</namePart>
<namePart type="family">Dattatreya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keren</namePart>
<namePart type="family">Artiaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushi</namePart>
<namePart type="given">Jaydeep</namePart>
<namePart type="family">Pujara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Železný</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Gruber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Honzík</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabyasachi</namePart>
<namePart type="family">Kamila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Facundo</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Quiroga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Hrúz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Hasanuzzaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-488-0</identifier>
</relatedItem>
<abstract>Isolated sign language recognition is commonly formulated as supervised classification, but this formulation is challenging when nearly every target gloss has only one labeled video. We study the Isolated Sign Language Recognition track of the WSLP 2026 Shared Task on Indian Sign Language Processing, a predominantly one-shot target setting with 4,398 training videos spanning 4,361 glosses, over 99% of which are singletons. We introduce CARE, a Coverage-Aware Retrieval Ensemble that augments a complete local visual dictionary with a CISLR reference bank covering a subset of the target vocabulary. A frozen Video-Swin encoder ranks all target labels locally, while frozen I3D and SignRep encoders provide external retrieval evidence for lexically matched labels. CARE estimates orthogonal Procrustes mappings from shared-class centroids, retains both raw and aligned representation geometries, and preserves external videos as individual nearest-neighbor references. Query-wise score standardization and a deterministic coverage mask restrict external evidence to supported labels. The method requires neither target-specific backbone fine-tuning nor a large-vocabulary classification head. CARE obtains 74.31%/76.15%/76.15% Top-1/5/10 accuracy on the WSLP 2026 validation split and 65.59%/67.11%/68.25% on the official test split. The 8.72% Top-1 gap warrants caution when interpreting performance on the small 109-query validation split used for model selection.</abstract>
<identifier type="citekey">nam-takahashi-2026-care</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.14/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>141</start>
<end>146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CARE: A Coverage-Aware Retrieval Ensemble for Isolated Sign Language Recognition
%A Nam, Nguyen Tu
%A Takahashi, Hiroki
%Y Singh, Sanjeet
%Y Joshi, Abhinav
%Y Dattatreya, Pokala
%Y Artiaga, Keren
%Y Pujara, Khushi Jaydeep
%Y Železný, Tomáš
%Y Gruber, Ivan
%Y Honzík, Jakub
%Y Kamila, Sabyasachi
%Y Quiroga, Facundo Manuel
%Y Hrúz, Marek
%Y Hasanuzzaman, Mohammed
%Y Modi, Ashutosh
%S Proceedings of the Second Workshop on Sign Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-488-0
%F nam-takahashi-2026-care
%X Isolated sign language recognition is commonly formulated as supervised classification, but this formulation is challenging when nearly every target gloss has only one labeled video. We study the Isolated Sign Language Recognition track of the WSLP 2026 Shared Task on Indian Sign Language Processing, a predominantly one-shot target setting with 4,398 training videos spanning 4,361 glosses, over 99% of which are singletons. We introduce CARE, a Coverage-Aware Retrieval Ensemble that augments a complete local visual dictionary with a CISLR reference bank covering a subset of the target vocabulary. A frozen Video-Swin encoder ranks all target labels locally, while frozen I3D and SignRep encoders provide external retrieval evidence for lexically matched labels. CARE estimates orthogonal Procrustes mappings from shared-class centroids, retains both raw and aligned representation geometries, and preserves external videos as individual nearest-neighbor references. Query-wise score standardization and a deterministic coverage mask restrict external evidence to supported labels. The method requires neither target-specific backbone fine-tuning nor a large-vocabulary classification head. CARE obtains 74.31%/76.15%/76.15% Top-1/5/10 accuracy on the WSLP 2026 validation split and 65.59%/67.11%/68.25% on the official test split. The 8.72% Top-1 gap warrants caution when interpreting performance on the small 109-query validation split used for model selection.
%U https://aclanthology.org/2026.wslp-1.14/
%P 141-146
Markdown (Informal)
[CARE: A Coverage-Aware Retrieval Ensemble for Isolated Sign Language Recognition](https://aclanthology.org/2026.wslp-1.14/) (Nam & Takahashi, WSLP 2026)
ACL