@inproceedings{skobov-bono-2023-making,
title = "Making Body Movement in Sign Language Corpus Accessible for Linguists and Machines with Three-Dimensional Normalization of {M}edia{P}ipe",
author = "Skobov, Victor and
Bono, Mayumi",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.124/",
doi = "10.18653/v1/2023.findings-emnlp.124",
pages = "1844--1855",
abstract = "Linguists can access movement in the sign language video corpus through manual annotation or computational methods. The first relies on a predefinition of features, and the second requires technical knowledge. Methods like MediaPipe and OpenPose are now more often used in sign language processing. MediaPipe detects a two-dimensional (2D) body pose in a single image with a limited approximation of the depth coordinate. Such 2D projection of a three-dimensional (3D) body pose limits the potential application of the resulting models outside the capturing camera settings and position. 2D pose data does not provide linguists with direct and human-readable access to the collected movement data. We propose our four main contributions: A novel 3D normalization method for MediaPipe`s 2D pose, a novel human-readable way of representing the 3D normalized pose data, an analysis of Japanese Sign Language (JSL) sociolinguistic features using the proposed techniques, where we show how an individual signer can be identified based on unique personal movement patterns suggesting a potential threat to anonymity. Our method outperforms the common 2D normalization on a small, diverse JSL dataset. We demonstrate its benefit for deep learning approaches by significantly outperforming the pose-based state-of-the-art models on the open sign language recognition benchmark."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skobov-bono-2023-making">
<titleInfo>
<title>Making Body Movement in Sign Language Corpus Accessible for Linguists and Machines with Three-Dimensional Normalization of MediaPipe</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Skobov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayumi</namePart>
<namePart type="family">Bono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Linguists can access movement in the sign language video corpus through manual annotation or computational methods. The first relies on a predefinition of features, and the second requires technical knowledge. Methods like MediaPipe and OpenPose are now more often used in sign language processing. MediaPipe detects a two-dimensional (2D) body pose in a single image with a limited approximation of the depth coordinate. Such 2D projection of a three-dimensional (3D) body pose limits the potential application of the resulting models outside the capturing camera settings and position. 2D pose data does not provide linguists with direct and human-readable access to the collected movement data. We propose our four main contributions: A novel 3D normalization method for MediaPipe‘s 2D pose, a novel human-readable way of representing the 3D normalized pose data, an analysis of Japanese Sign Language (JSL) sociolinguistic features using the proposed techniques, where we show how an individual signer can be identified based on unique personal movement patterns suggesting a potential threat to anonymity. Our method outperforms the common 2D normalization on a small, diverse JSL dataset. We demonstrate its benefit for deep learning approaches by significantly outperforming the pose-based state-of-the-art models on the open sign language recognition benchmark.</abstract>
<identifier type="citekey">skobov-bono-2023-making</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.124</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.124/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>1844</start>
<end>1855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Body Movement in Sign Language Corpus Accessible for Linguists and Machines with Three-Dimensional Normalization of MediaPipe
%A Skobov, Victor
%A Bono, Mayumi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F skobov-bono-2023-making
%X Linguists can access movement in the sign language video corpus through manual annotation or computational methods. The first relies on a predefinition of features, and the second requires technical knowledge. Methods like MediaPipe and OpenPose are now more often used in sign language processing. MediaPipe detects a two-dimensional (2D) body pose in a single image with a limited approximation of the depth coordinate. Such 2D projection of a three-dimensional (3D) body pose limits the potential application of the resulting models outside the capturing camera settings and position. 2D pose data does not provide linguists with direct and human-readable access to the collected movement data. We propose our four main contributions: A novel 3D normalization method for MediaPipe‘s 2D pose, a novel human-readable way of representing the 3D normalized pose data, an analysis of Japanese Sign Language (JSL) sociolinguistic features using the proposed techniques, where we show how an individual signer can be identified based on unique personal movement patterns suggesting a potential threat to anonymity. Our method outperforms the common 2D normalization on a small, diverse JSL dataset. We demonstrate its benefit for deep learning approaches by significantly outperforming the pose-based state-of-the-art models on the open sign language recognition benchmark.
%R 10.18653/v1/2023.findings-emnlp.124
%U https://aclanthology.org/2023.findings-emnlp.124/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.124
%P 1844-1855
Markdown (Informal)
[Making Body Movement in Sign Language Corpus Accessible for Linguists and Machines with Three-Dimensional Normalization of MediaPipe](https://aclanthology.org/2023.findings-emnlp.124/) (Skobov & Bono, Findings 2023)
ACL