Mutual Support of Data Modalities in the Task of Sign Language Recognition
| dc.contributor.author | Gruber, Ivan | |
| dc.contributor.author | Krňoul, Zdeněk | |
| dc.contributor.author | Hrúz, Marek | |
| dc.contributor.author | Kanis, Jakub | |
| dc.contributor.author | Boháček, Matyáš | |
| dc.date.accessioned | 2022-04-04T10:00:10Z | |
| dc.date.available | 2022-04-04T10:00:10Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract-translated | This paper presents a method for automatic sign language recognition that was utilized in the CVPR 2021 ChaLearn Challenge (RGB track). Our method is composed of several approaches combined in an ensemble scheme to perform isolated sign-gesture recognition. We combine modalities of video sample frames processed by a 3D ConvNet (I3D), with body-pose information in the form of joint locations processed by a Transformer, hand region images transformed into a semantic space, and linguistically defined locations of hands. Although the individual models perform sub-par (60% to 93% accuracy on validation data), the weighted ensemble results in 95.46% accuracy. | en |
| dc.format | 10 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | GRUBER, I. KRŇOUL, Z. HRÚZ, M. KANIS, J. BOHÁČEK, M. Mutual Support of Data Modalities in the Task of Sign Language Recognition. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Nashville: IEEE, 2021. s. 3419-3428. ISBN: 978-1-66544-899-4 , ISSN: 2160-7508 | cs |
| dc.identifier.document-number | 705890203056 | |
| dc.identifier.doi | 10.1109/CVPRW53098.2021.00381 | |
| dc.identifier.isbn | 978-1-66544-899-4 | |
| dc.identifier.issn | 2160-7508 | |
| dc.identifier.obd | 43933806 | |
| dc.identifier.uri | 2-s2.0-85116062397 | |
| dc.identifier.uri | http://hdl.handle.net/11025/47308 | |
| dc.language.iso | en | en |
| dc.project.ID | TN01000024/Národní centrum kompetence - Kybernetika a umělá inteligence - prodloužení | cs |
| dc.project.ID | EF15_003/0000466/Umělá inteligence a uvažování | cs |
| dc.publisher | IEEE | en |
| dc.relation.ispartofseries | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | en |
| dc.rights | Plný text je přístupný v rámci univerzity přihlášeným uživatelům. | cs |
| dc.rights | © IEEE | en |
| dc.rights.access | restrictedAccess | en |
| dc.subject | rozpoznávání znakového jazyka | cs |
| dc.subject | konvoluční neuronové sítě | cs |
| dc.subject.translated | sign language recognition | en |
| dc.subject.translated | convolutional neural networks | en |
| dc.title | Mutual Support of Data Modalities in the Task of Sign Language Recognition | en |
| dc.title.alternative | Vzájemná podpora datových modalit v úloze rozpoznávání znakového jazyka | cs |
| dc.type | konferenční příspěvek | cs |
| dc.type | ConferenceObject | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
Files
Original bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- Gruber_Mutual_Support_of_Data_Modalities_in_the_Task_of_Sign_CVPRW_2021_paper.pdf
- Size:
- 554.23 KB
- Format:
- Adobe Portable Document Format