Raman, Natraj and Maybank, Stephen J. (2015) Action classification using a discriminative multilevel HDP-HMM. Neurocomputing 154 , pp. 149-161. ISSN 0925-2312.
|
Text
11304.pdf - Author's Accepted Manuscript Download (1MB) | Preview |
Abstract
We classify human actions occurring in depth image sequences using features based on skeletal joint positions. The action classes are represented by a multi-level Hierarchical Dirichlet Process – Hidden Markov Model (HDP-HMM). The non-parametric HDP-HMM allows the inference of hidden states automatically from training data. The model parameters of each class are formulated as transformations from a shared base distribution, thus promoting the use of unlabelled examples during training and borrowing information across action classes. Further, the parameters are learnt in a discriminative way. We use a normalized gamma process representation of HDP and margin based likelihood functions for this purpose. We sample parameters from the complex posterior distribution induced by our discriminative likelihood function using elliptical slice sampling. Experiments with two different datasets show that action class models learnt using our technique produce good classification results.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | Action classification, Depth image sequences, HDP-HMM, Discriminative classification, Slice sampling |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
| Depositing User: | Administrator |
| Date Deposited: | 16 Dec 2014 14:00 |
| Last Modified: | 09 Aug 2023 12:35 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/11304 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
