AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Sequential Motif Profiles and Topological Plots for Offline Signature Verification

Elias N. Zois, Evangelos Zervas, Dimitrios Tsourounis, George Economou

CVPR 2020 · Graph learning › Graph self-supervised learning · approach: Brain and biological graph learning · 20 citations (OpenAlex)

Check 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
Represent signatures with local sequential visibility motifs and average-pool the codesOffline signature verification · CEDAREER(S): 0.51Improved
Represent signatures with local sequential visibility motifs and average-pool the codesOffline signature verification · MCYT-75EER(S): 1.54Mixed
Use local average-pooled motif features instead of global degree-distribution featuresVisibility-graph signature verification · CEDAREER(S) user_thresh: 18.6 -> 0.51Improved
Use local average-pooled motif features instead of global degree-distribution featuresVisibility-graph signature verification · MCYT-75EER(S) user_thresh: 23.3 -> 1.54Improved
Use horizontal motifs only rather than combining motif types (ablation)Visibility motif features · CEDAREER(S) user_thresh: 0.51 -> 0.30Improved
Use horizontal motifs only rather than combining motif types (ablation)Visibility motif features · MCYT-75EER(S) user_thresh: 1.54 -> 1.59No clear effect
Use natural motifs only rather than combining motif types (ablation)Visibility motif features · CEDAREER(S) user_thresh: 0.51 -> 1.01Hurt
Use natural motifs only rather than combining motif types (ablation)Visibility motif features · MCYT-75EER(S) user_thresh: 1.54 -> 2.03Hurt
Replace average pooling with max pooling (ablation)Visibility motif features · CEDAR and MCYT-75EER(S) user_thresh: CEDAR: 0.51 -> 17.0; MCYT-75: 1.54 -> 12.55Hurt
Replace average pooling with standard-deviation pooling (ablation)Visibility motif features · CEDAR and MCYT-75EER(S) user_thresh: CEDAR: 0.51 -> 1.99; MCYT-75: 1.54 -> 2.42Hurt
Combine average and standard-deviation pooling (ablation)Visibility motif features · CEDAR and MCYT-75EER(S) user_thresh: CEDAR: 0.51 -> 0.41; MCYT-75: 1.54 -> 1.61Mixed
Increase local patch size from 5 to 7 (ablation)Sequential motif features · CEDAR and MCYT-75EER(S): CEDAR: 0.04 -> 0.05; MCYT-75: 1.61 -> 1.67Hurt

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