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

Simon Jones, Ling Shao

Research output: Contribution to conferencePaper

35 Citations (Scopus)

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.
Original languageEnglish
DOIs
Publication statusPublished - Jun 2014
EventCVPR 2014 - IEEE Conference on Computer Vision and Pattern Recognition - Columbus, Ohio
Duration: 1 Jun 2014 → …

Conference

ConferenceCVPR 2014 - IEEE Conference on Computer Vision and Pattern Recognition
Period1/06/14 → …

Keywords

  • Clustering
  • Human Action Recognition
  • Manifold Learning
  • Multimedia Retrieval
  • Spectral Embedding
  • Unsupervised Learning

Fingerprint

Dive into the research topics of 'A Multigraph Representation for Improved Unsupervised/Semi-supervised Learning of Human Actions'. Together they form a unique fingerprint.

Cite this