There are two basic approaches how to segment continuous signing into individual signs:
A sign starts where the preceding one ends (i.e. fluent signing means there are no gaps between signs)
Transitional movements between signs do not count as part of either sign. Therefore, usually there are gaps between two signs during which the articulators move from the end of one sign to the beginning of the next.
Both approaches have their pros and cons. However, in the context of the DGS Corpus and the Dicta-Sign project the second approach offers advantages for the subsequent processing. Here we investigate how sensitive this approach is with respect to higher video frame rates.
@inproceedings{hanke:12028:sign-lang:lrec,
author = {Hanke, Thomas and Matthes, Silke and Regen, Anja and Worseck, Satu},
title = {Where Does a Sign Start and End? Segmentation of Continuous Signing},
pages = {69--74},
editor = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Kristoffersen, Jette and Mesch, Johanna},
booktitle = {Proceedings of the {LREC2012} 5th Workshop on the Representation and Processing of Sign Languages: Interactions between Corpus and Lexicon},
maintitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)},
publisher = {{European Language Resources Association (ELRA)}},
address = {Istanbul, Turkey},
day = {27},
month = may,
year = {2012},
language = {english},
url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/12028.pdf}
}