@inproceedings{yanovich-etal-2016-detection:lrec,
  author    = {Yanovich, Polina and Neidle, Carol and Metaxas, Dimitris},
  title     = {Detection of Major {ASL} Sign Types in Continuous Signing For {ASL} Recognition},
  pages     = {3067--3073},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios},
  booktitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Portoro{\v z}, Slovenia},
  day       = {23--28},
  month     = may,
  year      = {2016},
  isbn      = {978-2-9517408-9-1},
  language  = {english},
  url       = {https://aclanthology.org/L16-1490},
  doi       = {10.63317/2ut664kbgkq3},
  abstract  = {In American Sign Language (ASL) as well as other signed languages, different classes of signs (e.g., lexical signs, fingerspelled signs, and classifier constructions) have different internal structural properties. Continuous sign recognition accuracy can be improved through use of distinct recognition strategies, as well as different training datasets, for each class of signs. For these strategies to be applied, continuous signing video needs to be segmented into parts corresponding to particular classes of signs. In this paper we present a multiple instance learning-based segmentation system that accurately labels 91.27{\%} of the video frames of 500 continuous utterances (including 7 different subjects) from the publicly accessible NCSLGR corpus (Neidle and Vogler, 2012). The system uses novel feature descriptors derived from both motion and shape statistics of the regions of high local motion. The system does not require a hand tracker.}
}

@inproceedings{dilsizian-etal-2014-new:lrec,
  author    = {Dilsizian, Mark and Yanovich, Polina and Wang, Shu and Neidle, Carol and Metaxas, Dimitris},
  title     = {A New Framework for Sign Language Recognition based on 3{D} Handshape Identification and Linguistic Modeling},
  pages     = {1924--1929},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,},
  booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Reykjavik, Iceland},
  day       = {26--31},
  month     = may,
  year      = {2014},
  isbn      = {978-2-9517408-8-4},
  language  = {english},
  url       = {https://aclanthology.org/L14-1096},
  doi       = {10.63317/5evcpoxgej5n},
  abstract  = {Current approaches to sign recognition by computer generally have at least some of the following limitations: they rely on laboratory conditions for sign production, are limited to a small vocabulary, rely on 2D modeling (and therefore cannot deal with occlusions and off-plane rotations), and/or achieve limited success. Here we propose a new framework that (1) provides a new tracking method less dependent than others on laboratory conditions and able to deal with variations in background and skin regions (such as the face, forearms, or other hands); (2) allows for identification of 3D hand configurations that are linguistically important in American Sign Language (ASL); and (3) incorporates statistical information reflecting linguistic constraints in sign production. For purposes of large-scale computer-based sign language recognition from video, the ability to distinguish hand configurations accurately is critical. Our current method estimates the 3D hand configuration to distinguish among 77 hand configurations linguistically relevant for ASL. Constraining the problem in this way makes recognition of 3D hand configuration more tractable and provides the information specifically needed for sign recognition. Further improvements are obtained by incorporation of statistical information about linguistic dependencies among handshapes within a sign derived from an annotated corpus of almost 10,000 sign tokens.}
}