Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01HC9XHW6GGS2VRAYDSPHE6R26> ?p ?o. }
Showing items 1 to 31 of
31
with 100 items per page.
- 01HC9XHW6GGS2VRAYDSPHE6R26 classification P1.
- 01HC9XHW6GGS2VRAYDSPHE6R26 date "2023".
- 01HC9XHW6GGS2VRAYDSPHE6R26 language "eng".
- 01HC9XHW6GGS2VRAYDSPHE6R26 type conference.
- 01HC9XHW6GGS2VRAYDSPHE6R26 hasPart 01HC9XNKVBGNTJ71ZJVW64XW8B.pdf.
- 01HC9XHW6GGS2VRAYDSPHE6R26 hasPart 01HN2F8SY6G73QKGD2MWFHFKXQ.pdf.
- 01HC9XHW6GGS2VRAYDSPHE6R26 hasPart urn:uuid:e40c1c43-fde8-46fc-8bdf-5a55e0812f50.
- 01HC9XHW6GGS2VRAYDSPHE6R26 subject "Languages and Literatures".
- 01HC9XHW6GGS2VRAYDSPHE6R26 subject "Technology and Engineering".
- 01HC9XHW6GGS2VRAYDSPHE6R26 doi "10.1109/ICCVW60793.2023.00215".
- 01HC9XHW6GGS2VRAYDSPHE6R26 isbn "9798350307443".
- 01HC9XHW6GGS2VRAYDSPHE6R26 issn "2473-9936".
- 01HC9XHW6GGS2VRAYDSPHE6R26 issn "2473-9944".
- 01HC9XHW6GGS2VRAYDSPHE6R26 presentedAt urn:uuid:a9ebcc04-8f88-416b-907b-55bb0fcfe64b.
- 01HC9XHW6GGS2VRAYDSPHE6R26 abstract "One of the most significant challenges to sign language recognition (SLR) today is the low resource nature of sign language datasets, with many datasets being extremely low resource. Transfer learning is therefore a promising, and likely indispensable, method of increasing recognition performance. The use of pose estimation models, which are typically trained on a large and diverse population, can also aid generalization for extremely low resource sign languages. However, research on transfer learning for pose estimation keypoints as inputs has been limited. In this work, we explore transfer learning as a means to improve SLR classification performance for the extremely low resource Irish Sign Language (ISL). We show that transfer learning on larger datasets containing secondary sign languages significantly improves performance on our target sign language, ISL. To understand these results and the attributes that make one dataset better than another for pre-training, we analyse the linguistic relationships between these datasets. We find that certain attributes of datasets are associated with better transfer learning performance. We hope that our findings will not only motivate further research into transfer learning for pose keypoint-based SLR but also act as a practical guide to researchers on choosing the most suitable datasets with which to pre-train models.".
- 01HC9XHW6GGS2VRAYDSPHE6R26 author 39C8CCA0-F0EE-11E1-A9DE-61C894A0A6B4.
- 01HC9XHW6GGS2VRAYDSPHE6R26 author D65666C8-0208-11E3-BADE-15C210BDE39D.
- 01HC9XHW6GGS2VRAYDSPHE6R26 author urn:uuid:171a727c-aeee-4491-a8ad-345525fe3cab.
- 01HC9XHW6GGS2VRAYDSPHE6R26 author urn:uuid:2da8d4c4-5923-4ad2-8c7a-b5f5ec11b610.
- 01HC9XHW6GGS2VRAYDSPHE6R26 author urn:uuid:6cb602dc-e17a-42ac-922d-4e0f0822b45c.
- 01HC9XHW6GGS2VRAYDSPHE6R26 author urn:uuid:95c3c516-7476-4d17-b4a6-72e5982eddff.
- 01HC9XHW6GGS2VRAYDSPHE6R26 author urn:uuid:dc01767d-40e2-4021-b361-a9b95ce9310a.
- 01HC9XHW6GGS2VRAYDSPHE6R26 dateCreated "2023-10-09T09:51:06Z".
- 01HC9XHW6GGS2VRAYDSPHE6R26 dateModified "2024-10-29T18:38:50Z".
- 01HC9XHW6GGS2VRAYDSPHE6R26 name "From scarcity to understanding : transfer learning for the extremely low resource Irish sign language".
- 01HC9XHW6GGS2VRAYDSPHE6R26 pagination urn:uuid:d5a660f6-4b58-4ac4-95a2-03b57a4ad8ea.
- 01HC9XHW6GGS2VRAYDSPHE6R26 publisher urn:uuid:1c9375db-d1b3-4476-a95d-239bcd8e2c60.
- 01HC9XHW6GGS2VRAYDSPHE6R26 sameAs LU-01HC9XHW6GGS2VRAYDSPHE6R26.
- 01HC9XHW6GGS2VRAYDSPHE6R26 sourceOrganization urn:uuid:0b7a3fd2-c09d-42ad-8d56-3d7a5f2937fd.
- 01HC9XHW6GGS2VRAYDSPHE6R26 sourceOrganization urn:uuid:f31c89cd-f1be-49b1-a62e-997c18db4c3b.
- 01HC9XHW6GGS2VRAYDSPHE6R26 type P1.