Δημοσιεύσεις
2024
Papadimitriou, Katerina; Sapountzaki, Galini; Vasilaki, Kyriaki; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Potamianos, Gerasimos
A large corpus for the recognition of Greek Sign Language gestures Journal Article
In: Computer Vision and Image Understanding, pp. 104212, 2024, ISSN: 1077-3142.
@article{PAPADIMITRIOU2024104212,
title = {A large corpus for the recognition of Greek Sign Language gestures},
author = {Katerina Papadimitriou and Galini Sapountzaki and Kyriaki Vasilaki and Eleni Efthimiou and Stavroula-Evita Fotinea and Gerasimos Potamianos},
url = {https://www.sciencedirect.com/science/article/pii/S1077314224002935},
doi = {https://doi.org/10.1016/j.cviu.2024.104212},
issn = {1077-3142},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {Computer Vision and Image Understanding},
pages = {104212},
abstract = {Sign language recognition (SLR) from videos constitutes a captivating problem in gesture recognition, requiring the interpretation of hand movements, facial expressions, and body postures. The complexity of sign formation, signing variability among signers, and the technical hurdles of visual detection and tracking render SLR a challenging task. At the same time, the scarcity of large-scale SLR datasets, which are critical for developing robust data-intensive deep-learning SLR models, exacerbates these issues. In this article, we introduce a multi-signer video corpus of Greek Sign Language (GSL), which is the largest GSL database to date, serving as a valuable resource for SLR research. This corpus comprises an extensive RGB+D video collection that conveys rich lexical content in a multi-modal fashion, encompassing three subsets: (i) isolated signs; (ii) continuous signing; and (iii) continuous alphabet fingerspelling of words. Moreover, we introduce a comprehensive experimental setup that paves the way for more accurate and robust SLR solutions. In particular, except for the multi-signer (MS) and signer-independent (SI) settings, we employ a signer-adapted (SA) experimental paradigm, facilitating a comprehensive evaluation of system performance across various scenarios. Further, we provide three baseline SLR systems for isolated signs, continuous signing, and continuous fingerspelling. These systems leverage cutting-edge methods in deep learning and sequence modeling to capture the intricate temporal dynamics inherent in sign gestures. The models are evaluated on the three corpus subsets, setting their state-of-the-art recognition benchmark. The SL-ReDu GSL corpus, including its recommended experimental frameworks, is publicly available at https://sl-redu.e-ce.uth.gr/corpus.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Sign language recognition (SLR) from videos constitutes a captivating problem in gesture recognition, requiring the interpretation of hand movements, facial expressions, and body postures. The complexity of sign formation, signing variability among signers, and the technical hurdles of visual detection and tracking render SLR a challenging task. At the same time, the scarcity of large-scale SLR datasets, which are critical for developing robust data-intensive deep-learning SLR models, exacerbates these issues. In this article, we introduce a multi-signer video corpus of Greek Sign Language (GSL), which is the largest GSL database to date, serving as a valuable resource for SLR research. This corpus comprises an extensive RGB+D video collection that conveys rich lexical content in a multi-modal fashion, encompassing three subsets: (i) isolated signs; (ii) continuous signing; and (iii) continuous alphabet fingerspelling of words. Moreover, we introduce a comprehensive experimental setup that paves the way for more accurate and robust SLR solutions. In particular, except for the multi-signer (MS) and signer-independent (SI) settings, we employ a signer-adapted (SA) experimental paradigm, facilitating a comprehensive evaluation of system performance across various scenarios. Further, we provide three baseline SLR systems for isolated signs, continuous signing, and continuous fingerspelling. These systems leverage cutting-edge methods in deep learning and sequence modeling to capture the intricate temporal dynamics inherent in sign gestures. The models are evaluated on the three corpus subsets, setting their state-of-the-art recognition benchmark. The SL-ReDu GSL corpus, including its recommended experimental frameworks, is publicly available at https://sl-redu.e-ce.uth.gr/corpus.
Papadimitriou, Katerina; Potamianos, Gerasimos; Sapountzaki, Galini; Goulas, Theodoros; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Maragos, Petros
Greek sign language recognition for an education platform Journal Article
In: Universal Access in the Information Society, vol. 24, pp. 51-68, 2024, ISSN: 1615-5297.
@article{Papadimitriou_2023a,
title = {Greek sign language recognition for an education platform},
author = {Katerina Papadimitriou and Gerasimos Potamianos and Galini Sapountzaki and Theodoros Goulas and Eleni Efthimiou and Stavroula-Evita Fotinea and Petros Maragos},
url = {http://dx.doi.org/10.1007/s10209-023-01017-7},
doi = {10.1007/s10209-023-01017-7},
issn = {1615-5297},
year = {2024},
date = {2024-10-01},
urldate = {2023-07-01},
journal = {Universal Access in the Information Society},
volume = {24},
pages = {51-68},
publisher = {Springer Science and Business Media LLC},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2023
Sapountzaki, Galini; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Papadimitriou, Katerina; Potamianos, Gerasimos
Remote learning and assessment of Greek Sign Language in the undergraduate curriculum in COVID time Proceedings Article
In: EDULEARN23 Proceedings, IATED, 2023, ISSN: 2340-1117.
@inproceedings{Sapountzaki_2023,
title = {Remote learning and assessment of Greek Sign Language in the undergraduate curriculum in COVID time},
author = {Galini Sapountzaki and Eleni Efthimiou and Stavroula-Evita Fotinea and Katerina Papadimitriou and Gerasimos Potamianos},
url = {http://dx.doi.org/10.21125/edulearn.2023.1431},
doi = {10.21125/edulearn.2023.1431},
issn = {2340-1117},
year = {2023},
date = {2023-07-01},
urldate = {2023-07-01},
booktitle = {EDULEARN23 Proceedings},
publisher = {IATED},
series = {EDULEARN23},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Papadimitriou, Katerina; Sapountzaki, Galini; Vasilaki, Kiriaki; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Potamianos, Gerasimos
SL-REDU GSL: A Large Greek Sign Language Recognition Corpus Proceedings Article
In: 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2023.
@inproceedings{Papadimitriou_2023,
title = {SL-REDU GSL: A Large Greek Sign Language Recognition Corpus},
author = {Katerina Papadimitriou and Galini Sapountzaki and Kiriaki Vasilaki and Eleni Efthimiou and Stavroula-Evita Fotinea and Gerasimos Potamianos},
url = {http://dx.doi.org/10.1109/ICASSPW59220.2023.10193306},
doi = {10.1109/icasspw59220.2023.10193306},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
booktitle = {2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)},
publisher = {IEEE},
abstract = {We present a large multi-signer video corpus for the Greek Sign Language (GSL), suitable for the development and evaluation of GSL recognition algorithms. The database has been collected as part of the “SL-ReDu” project that focuses on the education use-case of systematic teaching of GSL as a second language (L2). The project aims to assist this process by allowing self-monitoring and objective assessment of GSL learners’ productions through the use of recognition technology, thus requiring suitable data resources relevant to the aforementioned use-case. To this end, we present the SL-ReDu GSL corpus, an extensive RGB+D video collection of 21 informants with a duration of 36 hours, recorded under studio conditions, consisting of: (i) isolated signs; (ii) continuous signing (annotated at the sentence level); and (iii) fingerspelling of words. We provide a detailed description of the design and acquisition methods used to develop it, along with corpus statistics and a comparison to existing sign language datasets. The SL-ReDu GSL corpus, as well as proposed frameworks for recognition experiments on it, are publicly available at https://www.sl-redu.e-ce.uth.gr/corpus.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We present a large multi-signer video corpus for the Greek Sign Language (GSL), suitable for the development and evaluation of GSL recognition algorithms. The database has been collected as part of the “SL-ReDu” project that focuses on the education use-case of systematic teaching of GSL as a second language (L2). The project aims to assist this process by allowing self-monitoring and objective assessment of GSL learners’ productions through the use of recognition technology, thus requiring suitable data resources relevant to the aforementioned use-case. To this end, we present the SL-ReDu GSL corpus, an extensive RGB+D video collection of 21 informants with a duration of 36 hours, recorded under studio conditions, consisting of: (i) isolated signs; (ii) continuous signing (annotated at the sentence level); and (iii) fingerspelling of words. We provide a detailed description of the design and acquisition methods used to develop it, along with corpus statistics and a comparison to existing sign language datasets. The SL-ReDu GSL corpus, as well as proposed frameworks for recognition experiments on it, are publicly available at https://www.sl-redu.e-ce.uth.gr/corpus.
2022
Sapountzaki, Galini; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Papadimitriou, Katerina; Potamianos, Gerasimos
3D GREEK SIGN LANGUAGE CLASSIFIERS AS A LEARNING OBJECT IN THE SL-REDU ONLINE EDUCATION PLATFORM Proceedings Article
In: EDULEARN22 Proceedings, pp. 6146–6153, IATED 2022.
@inproceedings{sapountzaki20223d,
title = {3D GREEK SIGN LANGUAGE CLASSIFIERS AS A LEARNING OBJECT IN THE SL-REDU ONLINE EDUCATION PLATFORM},
author = {Galini Sapountzaki and Eleni Efthimiou and Stavroula-Evita Fotinea and Katerina Papadimitriou and Gerasimos Potamianos},
year = {2022},
date = {2022-01-01},
booktitle = {EDULEARN22 Proceedings},
pages = {6146--6153},
organization = {IATED},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}