HaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognition

dc.contributor.authorNuzhdin, Anton
dc.contributor.authorNagaev, Alexander
dc.contributor.authorSautin, Alexander
dc.contributor.authorKapitanov, Alexander
dc.contributor.authorKvanchiani, Karina
dc.contributor.editorSkala, Václav
dc.date.accessioned2025-07-30T08:35:04Z
dc.date.available2025-07-30T08:35:04Z
dc.date.issued2025
dc.description.abstract-translatedThis paper proposes the second version of the widespread image-based Hand Gesture Recognition dataset HaGRID – HaGRIDv2. We have added 15 new gestures to the existing 18, encompassing both conversational and control functions, including two-handed gestures. Building on the foundational concepts proposed by HaGRID’s authors, we implemented the dynamic gesture recognition algorithm and further enhanced it by adding three new groups of manipulation gestures. The “no gesture” class was significantly expanded and redefined with a new semantic focus to include a diverse range of natural hand movements, which led to a 16-fold reduction in false positives on HaGRIDv2. The HaGRIDv2 dataset outperforms the original HaGRID in pre-training models for gesture-related tasks. Besides, we achieved the best generalization ability among gesture and hand detection datasets. Additionally, the second version of the dataset provides a diverse range of hand samples, which is crucial for fine-tuning modern diffusion models. By fine-tuning on HaGRIDv2, these models achieve improved outcomes in generating anatomically correct hand gesture images. HaGRIDv2, pre-trained models, and a dynamic gesture recognition algorithm are publicly available.en
dc.format14 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttp://www.doi.org/10.24132/CSRN.2025-1
dc.identifier.issn2464-4617 (Print)
dc.identifier.issn2464-4625 (online)
dc.identifier.urihttp://hdl.handle.net/11025/62207
dc.language.isoenen
dc.publisherVaclav Skala - UNION Agencyen
dc.rights© Vaclav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectrozpoznávání gest rukoucs
dc.subjectinterakce člověk-počítačcs
dc.subjectdatová sada HGRcs
dc.subject.translatedhand gesture recognitionen
dc.subject.translatedhuman-computer interactionen
dc.subject.translatedHGR Dataseen
dc.titleHaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognitionen
dc.typeconferenceObjecten
dc.typekonferenční příspěvekcs
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size7956223*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
A29.pdf
Size:
7.59 MB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: