# Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning

arXiv: https://arxiv.org/abs/2006.11812 · HTML: https://mlsanity.com/paper/2006.11812/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2020.

## Built on by (most cited first, 6 of 6)

- [Unsupervised Manifold Linearizing and Clustering](https://mlsanity.com/paper/2301.01805/) (2023)
- [Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance](https://mlsanity.com/paper/2204.10312/) (2022)
- [Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey](https://mlsanity.com/paper/2207.10574/) (2022)
- [A Novel Skeleton-Based Human Activity Discovery Using Particle Swarm Optimization with Gaussian Mutation](https://mlsanity.com/paper/2201.05314/) (2022)
- [GeoDynamics: A Geometric State-Space Neural Network for Understanding Brain Dynamics on Riemannian Manifolds](https://mlsanity.com/paper/2601.13570/) (2026)
- [ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization](https://mlsanity.com/paper/2505.17555/) (2025)

## Abstract (arXiv)

This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art approaches designed for this application are all supervised, in this paper we pursue a more challenging direction: Solving the problem with unsupervised learning. To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action's discriminability and a timestamp pruning approach that allow us to better handle the temporal dimension of the data. Through a broad experimental validation, we show that our computational pipeline surpasses existing unsupervised approaches but also can result in favorable performances as compared to supervised methods.