Paper Info
Title
Consistency and Diversity Induced Human Motion Segmentation
Abstract
Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation results. To this end, we propose a novel <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> onsistency and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b> iversity induced human <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> otion <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> egmentation (CDMS) algorithm. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces, in which transfer subspace learning is conducted on different layers to capture multi-level information. A multi-mutual consistency learning strategy is carried out to reduce the domain gap between the source and target data. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance. Moreover, to preserve the temporal correlations, an enhanced graph regularizer is imposed on the learned representation coefficients and the multi-level representations of the source data. The proposed model can be efficiently solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Extensive experimental results on public human motion datasets demonstrate the effectiveness of our method against several state-of-the-art approaches.
Year
DOI
Venue
2023
10.1109/TPAMI.2022.3147841
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Subspace clustering,human motion segmentation,transfer learning,multi-level representation
Journal
45
Issue
ISSN
Citations 
1
0162-8828
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Tao Zhou120921.34
Huazhu Fu2123565.07
Chen Gong340144.73
Ling Shao45424249.92
Fatih Porikli53409169.13
Haibin Ling64531215.76
Jianbing Shen758433.35