AI Paper Atlas

Research map / 3D vision / Human pose estimation

H2O: Two Hands Manipulating Objects for First Person Interaction Recognition

Taein Kwon, Bugra Tekin, Jan Stühmer, Federica Bogo, Marc Pollefeys

ICCV 2021 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 214 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add right-hand pose input to left-hand pose (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 33.61 -> 58.92Improved
add object pose to both hands pose (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 58.92 -> 79.25Improved
add hands-object interconnections to no interconnection (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 75.52 -> 78.84Improved
add left hand-right hand interconnections (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 75.52 -> 76.76Improved
add all interconnections over hands-object only (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 78.84 -> 79.25Improved
add Sj term (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 73.44 -> 79.25Improved
add Tj,inter term (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 75.52 -> 79.25Improved
add Tj,intra term (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 76.76 -> 79.25Improved
add Aj,inter term (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 76.35 -> 79.25Improved
add Aj,intra term (ablation)TA-GCN · H2O interaction recognition (test)accuracy (%): 77.59 -> 79.25Improved
use pose-based TA-GCN instead of image-based SlowFastaction recognition · H2O interaction recognition (test)accuracy (%): 77.69 -> 79.25Improved
use TA-GCN instead of ST-GCNpose-based recognition · H2O interaction recognition (test)accuracy (%): 73.86 -> 79.25Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy