# Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition

arXiv: https://arxiv.org/abs/1707.03993 · HTML: https://mlsanity.com/paper/1707.03993/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2017.

## Built on by (most cited first, 20 of 20)

- [Signature Methods in Machine Learning](https://mlsanity.com/paper/2206.14674/) (2022)
- [Framing RNN as a kernel method: A neural ODE approach](https://mlsanity.com/paper/2106.01202/) (2021)
- [SigKAN: Signature-Weighted Kolmogorov-Arnold Networks for Time Series](https://mlsanity.com/paper/2406.17890/) (2024)
- [Learning the Dynamics of Sparsely Observed Interacting Systems](https://mlsanity.com/paper/2301.11647/) (2023)
- [Path Signatures for Diversity in Probabilistic Trajectory Optimisation](https://mlsanity.com/paper/2308.04071/) (2023)
- [GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2403.15212/) (2024)
- [Explorative Imitation Learning: A Path Signature Approach for Continuous Environments](https://mlsanity.com/paper/2407.04856/) (2024)
- [Hedging with memory: shallow and deep learning with signatures](https://mlsanity.com/paper/2508.02759/) (2025)
- [ImageSig: A signature transform for ultra-lightweight image recognition](https://mlsanity.com/paper/2205.06929/) (2022)
- [A Neural RDE-based model for solving path-dependent PDEs](https://mlsanity.com/paper/2306.01123/) (2023)
- [Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling](https://mlsanity.com/paper/2312.03523/) (2023)
- [Clustering Digital Assets Using Path Signatures: Application to Portfolio Construction](https://mlsanity.com/paper/2410.23297/) (2024)
- [The path to a goal: Understanding soccer possessions via path signatures](https://mlsanity.com/paper/2508.12930/) (2025)
- [Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection](https://mlsanity.com/paper/2509.00931/) (2025)
- [Local regression on path spaces with signature metrics](https://mlsanity.com/paper/2510.16728/) (2025)
- [Path Signatures Enable Model-Free Mapping of RNA Modifications](https://mlsanity.com/paper/2511.08855/) (2025)
- [Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following](https://mlsanity.com/paper/2312.05547/) (2023)
- [Path Signatures and Graph Neural Networks for Slow Earthquake Analysis: Better Together?](https://mlsanity.com/paper/2402.03558/) (2024)
- [SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarios](https://mlsanity.com/paper/2505.18048/) (2025)
- [Rotation-free Online Handwritten Character Recognition Using Linear Recurrent Units](https://mlsanity.com/paper/2602.01533/) (2026)

## Abstract (arXiv)

Landmark-based human action recognition in videos is a challenging task in computer vision. One key step is to design a generic approach that generates discriminative features for the spatial structure and temporal dynamics. To this end, we regard the evolving landmark data as a high-dimensional path and apply non-linear path signature techniques to provide an expressive, robust, non-linear, and interpretable representation for the sequential events. We do not extract signature features from the raw path, rather we propose path disintegrations and path transformations as preprocessing steps. Path disintegrations turn a high-dimensional path linearly into a collection of lower-dimensional paths; some of these paths are in pose space while others are defined over a multiscale collection of temporal intervals. Path transformations decorate the paths with additional coordinates in standard ways to allow the truncated signatures of transformed paths to expose additional features. For spatial representation, we apply the signature transform to vectorize the paths that arise out of pose disintegration, and for temporal representation, we apply it again to describe this evolving vectorization. Finally, all the features are collected together to constitute the input vector of a linear single-hidden-layer fully-connected network for classification. Experimental results on four datasets demonstrated that the proposed feature set with only a linear shallow network and Dropconnect is effective and achieves comparable state-of-the-art results to the advanced deep networks, and meanwhile, is capable of interpretation.