Benchmarking 2D Egocentric Hand Pose Datasets

Hand pose estimation from egocentric video is a topic of significant interest with broad implications for human-computer interactions, assistive technologies, activity recognition, and robotics. The efficacy of modern machine learning models depends on the quality of data used for their training. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Olga Taran, Damian M. Manzone, Jose Zariffa
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015740/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849695393229570048
author Olga Taran
Damian M. Manzone
Jose Zariffa
author_facet Olga Taran
Damian M. Manzone
Jose Zariffa
author_sort Olga Taran
collection DOAJ
description Hand pose estimation from egocentric video is a topic of significant interest with broad implications for human-computer interactions, assistive technologies, activity recognition, and robotics. The efficacy of modern machine learning models depends on the quality of data used for their training. Thus, this work is devoted to the analysis of state-of-the-art egocentric datasets suitable for 2D hand pose estimation. We propose a novel protocol for dataset evaluation, which includes quantitative accuracy assessments, analysis of variability and challenging scenarios in dataset contents, realism, as well as the identification of dataset shortcomings through the performance evaluation of leading hand pose estimation models (OpenPose, DetNet, HRNetv2 and MediaPipe). Our study reveals that despite the availability of numerous egocentric databases intended for 2D hand pose estimation, the majority are tailored for specific use cases. There is no ideal benchmark dataset yet; however, H2O and GANerated Hands datasets emerge as the most promising real and synthetic datasets, respectively.
format Article
id doaj-art-017a85d0f44d4ddebc58b1ec96bb5f92
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-017a85d0f44d4ddebc58b1ec96bb5f922025-08-20T03:19:47ZengIEEEIEEE Access2169-35362025-01-0113924459245610.1109/ACCESS.2025.357373011015740Benchmarking 2D Egocentric Hand Pose DatasetsOlga Taran0https://orcid.org/0000-0001-8537-5204Damian M. Manzone1https://orcid.org/0000-0003-4152-0806Jose Zariffa2https://orcid.org/0000-0002-8842-745XKITE-Toronto Rehabilitation Institute, University Health Network, Toronto, ON, CanadaKITE-Toronto Rehabilitation Institute, University Health Network, Toronto, ON, CanadaKITE-Toronto Rehabilitation Institute, University Health Network, Toronto, ON, CanadaHand pose estimation from egocentric video is a topic of significant interest with broad implications for human-computer interactions, assistive technologies, activity recognition, and robotics. The efficacy of modern machine learning models depends on the quality of data used for their training. Thus, this work is devoted to the analysis of state-of-the-art egocentric datasets suitable for 2D hand pose estimation. We propose a novel protocol for dataset evaluation, which includes quantitative accuracy assessments, analysis of variability and challenging scenarios in dataset contents, realism, as well as the identification of dataset shortcomings through the performance evaluation of leading hand pose estimation models (OpenPose, DetNet, HRNetv2 and MediaPipe). Our study reveals that despite the availability of numerous egocentric databases intended for 2D hand pose estimation, the majority are tailored for specific use cases. There is no ideal benchmark dataset yet; however, H2O and GANerated Hands datasets emerge as the most promising real and synthetic datasets, respectively.https://ieeexplore.ieee.org/document/11015740/Benchmarkingdatasets2D hand pose estimationegocentric video
spellingShingle Olga Taran
Damian M. Manzone
Jose Zariffa
Benchmarking 2D Egocentric Hand Pose Datasets
IEEE Access
Benchmarking
datasets
2D hand pose estimation
egocentric video
title Benchmarking 2D Egocentric Hand Pose Datasets
title_full Benchmarking 2D Egocentric Hand Pose Datasets
title_fullStr Benchmarking 2D Egocentric Hand Pose Datasets
title_full_unstemmed Benchmarking 2D Egocentric Hand Pose Datasets
title_short Benchmarking 2D Egocentric Hand Pose Datasets
title_sort benchmarking 2d egocentric hand pose datasets
topic Benchmarking
datasets
2D hand pose estimation
egocentric video
url https://ieeexplore.ieee.org/document/11015740/
work_keys_str_mv AT olgataran benchmarking2degocentrichandposedatasets
AT damianmmanzone benchmarking2degocentrichandposedatasets
AT josezariffa benchmarking2degocentrichandposedatasets