UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

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

Yang, W; Lyons, T; Ni, H; Schmid, C; Jin, L; (2022) Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition. Stochastic Analysis, Filtering, and Stochastic Optimization: A Commemorative Volume to Honor Professor Mark H. A. Davis (In press).

[thumbnail of SignatureForAction.pdf] Text
SignatureForAction.pdf - Accepted Version
Access restricted to UCL open access staff until 23 June 2022.

Download (2MB)

Abstract

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.

Type: Article
Title: Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition
Publisher version: https://www.springer.com/series/4895
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Mathematics
URI: https://discovery.ucl.ac.uk/id/eprint/10140678
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item