Combining unsupervised learning and discrimination for 3D action recognition

Guang Chen, Daniel Clarke, Manuel Giuliani, Andre Gaschler, Alois Knoll

Research output: Contribution to journalArticlepeer-review

24 Scopus citations


Previous work on 3D action recognition has focused on using hand-designed features, either from depth videos or 2D videos. In this work, we present an effective way to combine unsupervised feature learning with discriminative feature mining. Unsupervised feature learning allows us to extract spatio-temporal features from unlabeled video data. With this, we can avoid the cumbersome process of designing feature extraction by hand. We propose an ensemble approach using a discriminative learning algorithm, where each base learner is a discriminative multi-kernel-learning classifier, trained to learn an optimal combination of joint-based features. Our evaluation includes a comparison to state-of-the-art methods on the MSRAction 3D dataset, where our method, abbreviated EnMkl, outperforms earlier methods. Furthermore, we analyze the efficiency of our approach in a 3D action recognition system.

Original languageEnglish
Pages (from-to)67-81
Number of pages15
JournalSignal Processing
StatePublished - May 2015


  • Depth camera
  • Ensemble learning
  • Human action recognition
  • Multi-kernel learning
  • Unsupervised learning


Dive into the research topics of 'Combining unsupervised learning and discrimination for 3D action recognition'. Together they form a unique fingerprint.

Cite this