AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Graph Constrained Data Representation Learning for Human Motion Segmentation

Mariella Dimiccoli, Lluís Garrido, Guillem Rodriguez-Corominas, Herwig Wendt

ICCV 2021 · Learning theory and algorithms › Clustering · approach: Subspace clustering · 7 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 auxiliary data matrix with graph constrained loss (ablation)temporal subspace clustering (TSC-style) model · WeizNMI: 0.8277 -> 0.9053Improved
add auxiliary data matrix with graph constrained loss (ablation)temporal subspace clustering (TSC-style) model · KeckNMI: 0.8000 -> 0.8325Improved
add auxiliary data matrix with graph constrained loss (ablation)temporal subspace clustering (TSC-style) model · UTNMI: 0.8176 -> 0.8256Improved
add auxiliary data matrix with graph constrained loss (ablation)temporal subspace clustering (TSC-style) model · MADNMI: 0.7529 -> 0.8471Improved
decrease relative weight of graph loss L_G by factor 10 (ablation)Ours · Weiz subject 1smoothness of auxiliary data: smoothness increased by a factor 10^0.7 ≈ 5-8 at 10^0.05 ≈ 10-15% increased deviationImproved
increase lambda_2 by two orders of magnitude (ablation)Ours · Weiz subject 1smoothness of auxiliary data: smoothness 10^0.3 ≈ 2 at more than 10^0.08 ≈ 20% larger deviationMixed
use graph constrained auxiliary data under added Gaussian noise vs TSC and LTS on raw dataOurs · Weiz subject 1 (noisy frames)NMIImproved
set temporal regularization lambda_2 very small (ablation)Ours · WeizNMIHurt
vary block-diagonal weight lambda_1 (ablation)Ours · WeizNMINo clear effect
vary graph filtering parameter h over two orders of magnitude (ablation)Ours · WeizNMINo clear effect

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