Research map / Label-efficient and robust learning / Recognition and long-tail
Static-Dynamic Interaction Networks for Offline Signature Verification
Huan Li, Ping Wei, Ping Hu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| introduce pseudo-dynamic sequence features through DR (ablation) | SDINet static representation · CEDAR | EER: 3.56 -> 2.18 | Improved |
| introduce pseudo-dynamic sequence features through DR (ablation) | SDINet static representation · BHSig-B | EER: 8.71 -> 7.51 | Improved |
| introduce pseudo-dynamic sequence features through DR (ablation) | SDINet static representation · BHSig-H | EER: 8.21 -> 6.15 | Improved |
| introduce dynamic-to-static attention (ablation) | SDINet static representation · CEDAR | EER: 3.56 -> 2.40 | Improved |
| introduce dynamic-to-static attention (ablation) | SDINet static representation · BHSig-B | EER: 8.71 -> 5.43 | Improved |
| introduce dynamic-to-static attention (ablation) | SDINet static representation · BHSig-H | EER: 8.21 -> 5.74 | Improved |
| combine DR with dynamic-to-static attention (ablation) | SDINet · GPDS | EER: 10.40 -> 10.43 | Hurt |
| use SDINet rather than Archetypes | CEDAR signature verification · CEDAR | EER: 2.07 -> 1.75 | Improved |
| use SDINet rather than FHTF | BHSig-B signature verification · BHSig-B | FAR: 10.36 -> 3.30 | Improved |
| use SDINet rather than IDN | BHSig-H signature verification · BHSig-H | Acc: 93.04 -> 95.00 | Improved |
| use SDINet rather than SigNet | GPDS signature verification · GPDS | Acc: 77.76 -> 89.66 | Improved |
Closest papers by meaning
- Sequential Motif Profiles and Topological Plots for Offline Signature Verification (CVPR 2020 · similarity 0.85)
- SynSig2Vec: Learning Representations from Synthetic Dynamic Signatures for Real-World Verification (AAAI 2020 · similarity 0.85)
- Offline Handwritten Signature Modeling and Verification Based on Archetypal Analysis (ICCV 2017 · similarity 0.84)
- SynSig2Vec: Forgery-Free Learning of Dynamic Signature Representations by Sigma Lognormal-Based Synthesis and 1D CNN (TPAMI 2021 · similarity 0.84)
- SignGraph: A Sign Sequence is Worth Graphs of Nodes (CVPR 2024 · similarity 0.80)
- TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions (AAAI 2024 · similarity 0.80)
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.
