AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition

Xuan Son Nguyen

ICCV 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Geometry of low-rank and SPD structure · 34 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 parallel transport in covariance computation (ablation)GeomNet · SBU Interactionaccuracy (%): 71.51 -> 96.33Improved
add parallel transport in covariance computation (ablation)GeomNet · NTU RGB+D 60 X-Subjectaccuracy (%): 62.18 -> 93.62Improved
add parallel transport in covariance computation (ablation)GeomNet · NTU RGB+D 60 X-Viewaccuracy (%): 66.83 -> 96.32Improved
add lower triangular matrix learning layer (ablation)GeomNet · SBU Interactionaccuracy (%): 94.90 -> 96.33Improved
add lower triangular matrix learning layer (ablation)GeomNet · NTU RGB+D 60 X-Subjectaccuracy (%): 92.30 -> 93.62Improved
add lower triangular matrix learning layer (ablation)GeomNet · NTU RGB+D 60 X-Viewaccuracy (%): 95.05 -> 96.32Improved
use (k,k')=(2,3) instead of (1,1) in Gaussian embedding (ablation)GeomNet · SBU Interactionaccuracy (%): 94.54 -> 96.33Improved
embed Gaussians with k=10 instead of k=1 in SPDNet (ablation)SPDNet · SBU Interactionaccuracy (%): 90.5 -> 92.38Improved
add the mean vector via Gaussian embedding (k=10) rather than covariance only (k=0) (ablation)SPDNet · SBU Interactionaccuracy (%): 79.48 -> 92.38Improved
use GeomNet instead of SPDNetSPDNet · SBU Interactionaccuracy (%): 92.38 -> 96.33Improved
use GeomNet instead of ST-GCN-PAMST-GCN-PAM · NTU RGB+D 120 X-Subjectaccuracy (%): 83.28 -> 86.49Improved
use AS-GCN actional and structural links instead of ST-GCNST-GCN · NTU RGB+D 60 X-Subjectaccuracy (%): 86.75 -> 87.08No clear effect

Later papers that compared with this method

1 later accepted paper reports GeomNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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