3D-LEX v1.0 - 3D Lexicons for American Sign Language and Sign Language of the Netherlands. Ranum, O., Otterspeer, G., Andersen, J., Belleman, R., & Roelofsen, F. In Proceedings of the LREC-COLING 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources, pages 290–301, Torino, Italy, May, 2024. ELRA and ICCL. ![3D-LEX v1.0 - 3D Lexicons for American Sign Language and Sign Language of the Netherlands [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex 5 downloads In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, to attain an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5% over using no handshape annotations, and by 1% over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.
@InProceedings{ranum-EtAl:2024:signlang,
author = {Ranum, Oline and Otterspeer, Gom{\`e}r and Andersen, Jari and Belleman, Robert and Roelofsen, Floris},
title = {3D-LEX v1.0 - 3D Lexicons for American Sign Language and Sign Language of the Netherlands},
booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources},
month = {May},
year = {2024},
address = {Torino, Italy},
publisher = {ELRA and ICCL},
pages = {290--301},
abstract = {In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, to attain an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5\% over using no handshape annotations, and by 1\% over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.},
url = {https://aclanthology.org/2024.signlang-1.33}
}
Downloads: 5
{"_id":"JeucXBEdjkJdKM5jT","bibbaseid":"ranum-otterspeer-andersen-belleman-roelofsen-3dlexv103dlexiconsforamericansignlanguageandsignlanguageofthenetherlands-2024","author_short":["Ranum, O.","Otterspeer, G.","Andersen, J.","Belleman, R.","Roelofsen, F."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Ranum"],"firstnames":["Oline"],"suffixes":[]},{"propositions":[],"lastnames":["Otterspeer"],"firstnames":["Gomèr"],"suffixes":[]},{"propositions":[],"lastnames":["Andersen"],"firstnames":["Jari"],"suffixes":[]},{"propositions":[],"lastnames":["Belleman"],"firstnames":["Robert"],"suffixes":[]},{"propositions":[],"lastnames":["Roelofsen"],"firstnames":["Floris"],"suffixes":[]}],"title":"3D-LEX v1.0 - 3D Lexicons for American Sign Language and Sign Language of the Netherlands","booktitle":"Proceedings of the LREC-COLING 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources","month":"May","year":"2024","address":"Torino, Italy","publisher":"ELRA and ICCL","pages":"290–301","abstract":"In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, to attain an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5% over using no handshape annotations, and by 1% over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.","url":"https://aclanthology.org/2024.signlang-1.33","bibtex":"@InProceedings{ranum-EtAl:2024:signlang,\n author = {Ranum, Oline and Otterspeer, Gom{\\`e}r and Andersen, Jari and Belleman, Robert and Roelofsen, Floris},\n title = {3D-LEX v1.0 - 3D Lexicons for American Sign Language and Sign Language of the Netherlands},\n booktitle = {Proceedings of the {LREC-COLING} 2024 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources},\n month = {May},\n year = {2024},\n address = {Torino, Italy},\n publisher = {ELRA and ICCL},\n pages = {290--301},\n abstract = {In this work, we present an efficient approach for capturing sign language in 3D, introduce the 3D-LEX v1.0 dataset, and detail a method for semi-automatic annotation of phonetic properties. Our procedure integrates three motion capture techniques encompassing high-resolution 3D poses, 3D handshapes, and depth-aware facial features, to attain an average sampling rate of one sign every 10 seconds. This includes the time for presenting a sign example, performing and recording the sign, and archiving the capture. The 3D-LEX dataset includes 1,000 signs from American Sign Language and an additional 1,000 signs from the Sign Language of the Netherlands. We showcase the dataset utility by presenting a simple method for generating handshape annotations directly from 3D-LEX. We produce handshape labels for 1,000 signs from American Sign Language and evaluate the labels in a sign recognition task. The labels enhance gloss recognition accuracy by 5\\% over using no handshape annotations, and by 1\\% over expert annotations. Our motion capture data supports in-depth analysis of sign features and facilitates the generation of 2D projections from any viewpoint. The 3D-LEX collection has been aligned with existing sign language benchmarks and linguistic resources, to support studies in 3D-aware sign language processing.},\n url = {https://aclanthology.org/2024.signlang-1.33}\n}\n\n\n","author_short":["Ranum, O.","Otterspeer, G.","Andersen, J.","Belleman, R.","Roelofsen, F."],"key":"ranum-EtAl:2024:signlang","id":"ranum-EtAl:2024:signlang","bibbaseid":"ranum-otterspeer-andersen-belleman-roelofsen-3dlexv103dlexiconsforamericansignlanguageandsignlanguageofthenetherlands-2024","role":"author","urls":{"Paper":"https://aclanthology.org/2024.signlang-1.33"},"metadata":{"authorlinks":{}},"downloads":5},"bibtype":"inproceedings","biburl":"www.signlab-amsterdam.nl/bib/signlab.bib","dataSources":["R8Za3BGYPnYDXtHHL","CEDzXuZSHaKCtJZEA"],"keywords":[],"search_terms":["lex","lexicons","american","sign","language","sign","language","netherlands","ranum","otterspeer","andersen","belleman","roelofsen"],"title":"3D-LEX v1.0 - 3D Lexicons for American Sign Language and Sign Language of the Netherlands","year":2024,"downloads":5}