A Multigraph Representation for Improved Unsupervised/Semi-supervised Learning of Human Actions

Jones, Simon and Shao, Ling (2014) A Multigraph Representation for Improved Unsupervised/Semi-supervised Learning of Human Actions. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014-06-23 - 2014-06-28, Columbus, OH, USA.

Full text not available from this repository.

Abstract

Graph-based methods are a useful class of methods for improving the performance of unsupervised and semi-supervised machine learning tasks, such as clustering or information retrieval. However, the performance of existing graph-based methods is highly dependent on how well the affinity graph reflects the original data structure. We propose that multimedia such as images or videos consist of multiple separate components, and therefore more than one graph is required to fully capture the relationship between them. Accordingly, we present a new spectral method - the Feature Grouped Spectral Multigraph (FGSM) - which comprises the following steps. First, mutually independent subsets of the original feature space are generated through feature clustering. Secondly, a separate graph is generated from each feature subset. Finally, a spectral embedding is calculated on each graph, and the embeddings are scaled/aggregated into a single representation. Using this representation, a variety of experiments are performed on three learning tasks - clustering, retrieval and recognition - on human action datasets, demonstrating considerably better performance than the state-of-the-art.

Item Type: Conference or Workshop Item (Other)
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Pure Connector
Date Deposited: 10 Feb 2017 02:29
Last Modified: 21 Oct 2022 23:42
URI: https://ueaeprints.uea.ac.uk/id/eprint/62418
DOI: 10.1109/CVPR.2014.110

Actions (login required)

View Item View Item