Publication:
Child Head Gesture Classification through Transformers

Simple item page
dc.contributor.authorWedasingha, N
dc.contributor.authorSamarasinghe, P
dc.contributor.authorSingarathnam, D
dc.contributor.authorPapandrea, M
dc.contributor.authorPuiatti, A
dc.contributor.authorSeneviratne, L
dc.date.accessioned2023-01-23T10:54:32Z
dc.date.available2023-01-23T10:54:32Z
dc.date.issued2022-11-04
dc.description.abstractThis paper proposes a transformer network for head pose classification (HPC) which outperforms the existing SoA for HPC. This robust model is then extended to overcome the limited child data challenge by applying transfer learning resulting in an accuracy of 95.34% for child HPC in the wild.en_US
dc.identifier.citationN. Wedasingha, P. Samarasinghe, D. Singarathnam, M. Papandrea, A. Puiatti and L. Seneviratne, "Child Head Gesture Classification through Transformers," TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON), Hong Kong, Hong Kong, 2022, pp. 1-6, doi: 10.1109/TENCON55691.2022.9977990.en_US
dc.identifier.doi10.1109/TENCON55691.2022.9977990en_US
dc.identifier.issn21593442
dc.identifier.urihttps://rda.sliit.lk/handle/123456789/3142
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofseriesIEEE Region 10 Annual International Conference, Proceedings/TENCON;
dc.subjectHead Pose Estimationen_US
dc.subjectLogistic Regressionen_US
dc.subjectSVMen_US
dc.subjectTransfer Learningen_US
dc.subjectTransformeren_US
dc.titleChild Head Gesture Classification through Transformersen_US
dc.typeArticleen_US
dspace.entity.typePublication

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Child_Head_Gesture_Classification_through_Transformers.pdf
Size:
780.84 KB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Information Technology