Skip to Main content Skip to Navigation
Conference papers

Graph Constrained Data Representation Learning for Human Motion Segmentation

Abstract : Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage prior knowledge from a source domain to improve clustering performance on a target domain, and currently they represent the state of the art in HMS. Bucking this trend, in this paper, we propose a novel unsupervised model that learns a representation of the data and digs clustering information from the data itself. Our model is reminiscent of temporal subspace clustering, but presents two critical differences. First, we learn an auxiliary data matrix that can deviate from the initial data, hence confers more degrees of freedom to the coding matrix. Second, we introduce a regularization term for this auxiliary data matrix that preserves the local geometrical structure present in the high-dimensional space. The proposed model is efficiently optimized by using an original Alternating Direction Method of Multipliers (ADMM) formulation allowing to learn jointly the auxiliary data representation, a nonnegative dictionary and a coding matrix. Experimental results on four benchmark datasets for HMS demonstrate that our approach achieves significantly better clustering performance then state-of-the-art methods, including both unsupervised and more recent semi-supervised transfer learning approaches 1 .
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03381930
Contributor : Herwig Wendt Connect in order to contact the contributor
Submitted on : Monday, October 18, 2021 - 9:45:39 AM
Last modification on : Thursday, November 4, 2021 - 10:13:46 AM

File

07078.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03381930, version 1

Citation

Mariella Dimiccoli, Lluís Garrido, Guillem Rodriguez-Corominas, Herwig Wendt. Graph Constrained Data Representation Learning for Human Motion Segmentation. 1st International Conference on Computer Vision (ICCV 2021), Oct 2021, Montreal (virtual), Canada. ⟨hal-03381930⟩

Share

Metrics

Record views

54

Files downloads

28