Developing the Path Signature Methodology and Its Application to Landmark- Based Human Action Recognition

DOI10.1007/978-3-030-98519-6_18OpenAlexW2994713923MaRDI QIDQ5050098

Lianwen Jin, Terence J. Lyons, Weixin Yang, Cordelia Schmid, Hao Ni

Publication date: 15 November 2022

Published in: Stochastic Analysis, Filtering, and Stochastic Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1707.03993

zbMATH Keywords

human action recognitionpath signature feature

Mathematics Subject Classification ID

Machine vision and scene understanding (68T45)

Related Items (1)

Sig‐Wasserstein GANs for conditional time series generation

Uses Software

• GitHub
• iisignature
• RMPE
• NeuralCDE
• torchcde
• NTU RGB+D
• CMU Motion Capture

Cites Work

• The signature of a rough path: uniqueness
• Uniqueness of signature for simple curves
• Discretely sampled signals and the rough Hoff process
• Uniqueness for the signature of a path of bounded variation and the reduced path group
• A practical guide to splines
• Differential equations driven by rough signals
• Integration of Paths--A Faithful Representation of Paths by Noncommutative Formal Power Series
• Learning with Signatures
• Learning Paths from Signature Tensors
• VARIETIES OF SIGNATURE TENSORS
• Kernels for sequentially ordered data
• A Survey of Computer Vision-Based Human Motion Capture
• A Comparative Review of Recent Kinect-Based Action Recognition Algorithms

This page was built for publication: Developing the Path Signature Methodology and Its Application to Landmark- Based Human Action Recognition