# GAFSV-Net: A Vision Framework for Online Signature Verification

arXiv: https://arxiv.org/abs/2605.00120 · HTML: https://mlsanity.com/paper/2605.00120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Classification of Time-Series Images Using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1710.00886/) (2017)
- [DeepSign: Deep On-Line Signature Verification](https://mlsanity.com/paper/2002.10119/) (2020)
- [BiosecurID: a multimodal biometric database](https://mlsanity.com/paper/2111.03472/) (2021)
- [OSVNet: Convolutional Siamese Network for Writer Independent Online Signature Verification](https://mlsanity.com/paper/1904.00240/) (2019)
- [Exploring Transformers for On-Line Handwritten Signature Verification](https://mlsanity.com/paper/2307.01663/) (2023)

## Abstract (arXiv)

Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few enrollment samples. Existing deep learning methods operate directly on raw temporal sequences, restricting them to 1D architectures and preventing the use of pretrained 2D vision backbones. We bridge this gap with GAFSV-Net, which represents each signature as a six-channel asymmetric Gramian Angular Field image: three kinematic channels (pen speed, pressure derivative, direction angle) are each encoded into complementary GASF and GADF matrices that capture pairwise temporal co-occurrence and directional transition structure respectively. A dual-branch ConvNeXt-Tiny encoder processes GASF and GADF independently, with bidirectional cross-attention enabling each branch to query discriminative patterns from the other before metric-space projection. Training uses semi-hard triplet loss with skilled-forgery hard-negative injection; verification is performed via cosine similarity against a small enrollment prototype. We evaluate on DeepSignDB and BiosecurID, outperforming all sequence-based baselines trained under identical objectives, demonstrating that the representational gain of 2D temporal encoding is consistent and independent of training procedure, with ablations characterising each design choice's contribution.