2014.11.04 |
Establishment of Kinect Sign Language Working Group |
2014.11.04 |
Publishment of DEVISIGN Subsets |
2014.11.04 Establishment of Kinect Sign Language Working Group
In order to collaborate more experts in the field of Kinect Sign Language Research, Microsoft Research established Kinect Sign Language Working Group together with the Chinese Academy of Sciences and Beijing Union University.
The research team hopes to partner with more experts in the world to establish a research community for advancing the state of the art of sign language recognition research in this field. Each member of the community can share the Kinect database for sign language recognition as well as algorithm with others.
2014.11.04 Publishment of DEVISIGN Subsets
The DEVISIGN database has been constructed under the sponsors of Microsoft Research Asia by VIPL Group, ICT, CAS. The goals to create the Chinese Sign Language database include: provide the worldwide researchers of SLR community a large Chinese vocabulary SL database for training and evaluating their algorithms; advance the state-of-the-art SLR technologies aiming at practical applications, especially for the unknown signer situation.
Currently, the DEVISIGN database covers 4,414 standard Chinese Sign Language vocabularies and in total contains 331,050 vocabulary data of 30 individuals (13 males and 17 females).
In the first stage, this DEVISIGN database is partly made available for research purposes. Three subsets of the whole DEVISIGN database have now been made publicly available. The first subset is composed of 26 letters and 10 numbers, the second subset is composed of 500 daily used vocabularies and the third subset is a large vocabulary dataset, which contains 2,000 Chinese SL vocabularies.
For more information, please refer to the Data page.
Copyright © 2014