@inproceedings{saunders:70001:sltat:lrec,
  author    = {Saunders, Ben and Camg{\"o}z, Necati Cihan and Bowden, Richard},
  title     = {Skeletal Graph Self-Attention: Embedding a Skeleton Inductive Bias into Sign Language Production},
  pages     = {95--102},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and McDonald, John C. and Shterionov, Dimitar and Wolfe, Rosalee},
  booktitle = {Proceedings of the 7th International Workshop on Sign Language Translation and Avatar Technology: The Junction of the Visual and the Textual: Challenges and Perspectives},
  maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Marseille, France},
  day       = {24},
  month     = jun,
  year      = {2022},
  isbn      = {979-10-95546-82-5},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/2022.sltat-1.15.html},
  abstract  = {Recent approaches to Sign Language Production (SLP) have adopted spoken language Neural Machine Translation (NMT) architectures, applied without sign-specific modifications. In addition, these works represent sign language as a sequence of skeleton pose vectors, projected to an abstract representation with no inherent skeletal structure. In this paper, we represent sign language sequences as a skeletal graph structure, with joints as nodes and both spatial and temporal connections as edges. To operate on this graphical structure, we propose Skeletal Graph Self-Attention (SGSA), a novel graphical attention layer that embeds a skeleton inductive bias into the SLP model. Retaining the skeletal feature representation throughout, we directly apply a spatio-temporal adjacency matrix into the self-attention formulation. This provides structure and context to each skeletal joint that is not possible when using a non-graphical abstract representation, enabling fluid and expressive sign language production. We evaluate our Skeletal Graph Self-Attention architecture on the challenging RWTH-PHOENIX-Weather-2014T (PHOENIX14T) dataset, achieving state-of-the-art back translation performance with an 8{\%} and 7{\%} improvement over competing methods for the dev and test sets.}
}

@inproceedings{tornay-etal-2020-hmm:lrec,
  author    = {Tornay, Sandrine and Aran, Oya and Magimai Doss, Mathew},
  title     = {An {HMM} Approach with Inherent Model Selection for Sign Language and Gesture Recognition},
  pages     = {6049--6056},
  editor    = {Calzolari, Nicoletta and Fr{\'e}d{\'e}ric B{\'e}chet and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios},
  booktitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Marseille, France},
  day       = {11--16},
  month     = may,
  year      = {2020},
  isbn      = {979-10-95546-34-4},
  language  = {english},
  url       = {https://aclanthology.org/2020.lrec-1.741},
  abstract  = {HMMs have been the one of the first models to be applied for sign recognition and have become the baseline models due to their success in modeling sequential and multivariate data. Despite the extensive use of HMMs for sign recognition, determining the HMM structure has still remained as a challenge, especially when the number of signs to be modeled is high. In this work, we present a continuous HMM framework for modeling and recognizing isolated signs, which inherently performs model selection to optimize the number of states for each sign separately during recognition. Our experiments on three different datasets, namely, German sign language DGS dataset, Turkish sign language HospiSign dataset and Chalearn14 dataset show that the proposed approach achieves better sign language or gesture recognition systems in comparison to the approach of selecting or presetting the number of HMM states based on k-means, and yields systems that perform competitive to the case where the number of states are determined based on the test set performance.}
}

@inproceedings{ebling-etal-2018-smile:lrec,
  author    = {Ebling, Sarah and Camg{\"o}z, Necati Cihan and Boyes Braem, Penny and Tissi, Katja and Sidler-Miserez, Sandra and Stoll, Stephanie and Hadfield, Simon and Haug, Tobias and Bowden, Richard and Tornay, Sandrine and Razavi, Marzieh and Magimai Doss, Mathew},
  title     = {{SMILE} {S}wiss {G}erman Sign Language Dataset},
  pages     = {4221--4229},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo,  H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu},
  booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Miyazaki, Japan},
  day       = {7--12},
  month     = may,
  year      = {2018},
  isbn      = {979-10-95546-00-9},
  language  = {english},
  url       = {https://aclanthology.org/L18-1666},
  abstract  = {Sign language recognition (SLR) involves identifying the form and meaning of isolated signs or sequences of signs. To our knowledge, the combination of SLR and sign language assessment is novel. The goal of an ongoing three-year project in Switzerland is to pioneer an assessment system for lexical signs of Swiss German Sign Language (Deutschschweizerische Geb{\"a}rdensprache, DSGS) that relies on SLR. The assessment system aims to give adult L2 learners of DSGS feedback on the correctness of the manual parameters (handshape, hand position, location, and movement) of isolated signs they produce. In its initial version, the system will include automatic feedback for a subset of a DSGS vocabulary production test consisting of 100 lexical items. To provide the SLR component of the assessment system with sufficient training samples, a large-scale dataset containing videotaped repeated productions of the 100 items of the vocabulary test with associated transcriptions and annotations was created, consisting of data from 11 adult L1 signers and 19 adult L2 learners of DSGS. This paper introduces the dataset, which will be made available to the research community.}
}