@inproceedings{apurbo-etal-2026-multiple,
title = "Multiple-Instance Contrastive Alignment for Pose-Based Sign Spotting",
author = "Apurbo, Md. Mosharaf Hossain and
Ali, Md. Asif and
Hasan, Kazi Reyazul",
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-1.8/",
pages = "77--83",
ISBN = "979-8-89176-488-0",
abstract = "Sign spotting, the task of deciding whether an isolated query sign occurs inside a clip of continuous signing, enables sign language video retrieval without gloss or text annotation. We describe our system for the WSLP@EMNLP-2026 Word/Sign Presence Prediction shared task on Indian Sign Language: a lightweight (2.86M-parameter) pose-based Siamese encoder that embeds both clips in one space, forms an explicit frame-to-frame cosine similarity map, and reduces it with multiple-instance pooling over temporal windows. Training combines binary cross-entropy with a multiple-instance contrastive objective (MIL-NCE). The system reaches 72.69 accuracy and 71.95 macro-F1 on the blind test set, against 61.66 and 58.42 for the published pose baseline on the same data. Ablations identify contrastive alignment as the component that makes the architecture work: the MIL-NCE objective is what places the two clips in a comparable metric space, and training does not leave chance without it. We further document a label-balance property of the released splits that fixes 76.3{\%} of blind test labels without a model, and recommend a change for future editions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="apurbo-etal-2026-multiple">
<titleInfo>
<title>Multiple-Instance Contrastive Alignment for Pose-Based Sign Spotting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mosharaf</namePart>
<namePart type="given">Hossain</namePart>
<namePart type="family">Apurbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Asif</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazi</namePart>
<namePart type="given">Reyazul</namePart>
<namePart type="family">Hasan</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>Sign spotting, the task of deciding whether an isolated query sign occurs inside a clip of continuous signing, enables sign language video retrieval without gloss or text annotation. We describe our system for the WSLP@EMNLP-2026 Word/Sign Presence Prediction shared task on Indian Sign Language: a lightweight (2.86M-parameter) pose-based Siamese encoder that embeds both clips in one space, forms an explicit frame-to-frame cosine similarity map, and reduces it with multiple-instance pooling over temporal windows. Training combines binary cross-entropy with a multiple-instance contrastive objective (MIL-NCE). The system reaches 72.69 accuracy and 71.95 macro-F1 on the blind test set, against 61.66 and 58.42 for the published pose baseline on the same data. Ablations identify contrastive alignment as the component that makes the architecture work: the MIL-NCE objective is what places the two clips in a comparable metric space, and training does not leave chance without it. We further document a label-balance property of the released splits that fixes 76.3% of blind test labels without a model, and recommend a change for future editions.</abstract>
<identifier type="citekey">apurbo-etal-2026-multiple</identifier>
<location>
<url>https://aclanthology.org/2026.wslp-1.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>77</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multiple-Instance Contrastive Alignment for Pose-Based Sign Spotting
%A Apurbo, Md. Mosharaf Hossain
%A Ali, Md. Asif
%A Hasan, Kazi Reyazul
%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 apurbo-etal-2026-multiple
%X Sign spotting, the task of deciding whether an isolated query sign occurs inside a clip of continuous signing, enables sign language video retrieval without gloss or text annotation. We describe our system for the WSLP@EMNLP-2026 Word/Sign Presence Prediction shared task on Indian Sign Language: a lightweight (2.86M-parameter) pose-based Siamese encoder that embeds both clips in one space, forms an explicit frame-to-frame cosine similarity map, and reduces it with multiple-instance pooling over temporal windows. Training combines binary cross-entropy with a multiple-instance contrastive objective (MIL-NCE). The system reaches 72.69 accuracy and 71.95 macro-F1 on the blind test set, against 61.66 and 58.42 for the published pose baseline on the same data. Ablations identify contrastive alignment as the component that makes the architecture work: the MIL-NCE objective is what places the two clips in a comparable metric space, and training does not leave chance without it. We further document a label-balance property of the released splits that fixes 76.3% of blind test labels without a model, and recommend a change for future editions.
%U https://aclanthology.org/2026.wslp-1.8/
%P 77-83
Markdown (Informal)
[Multiple-Instance Contrastive Alignment for Pose-Based Sign Spotting](https://aclanthology.org/2026.wslp-1.8/) (Apurbo et al., WSLP 2026)
ACL