Please use this identifier to cite or link to this item:
Title: A deep structured model with radius-margin bound for 3D human activity recognition
Authors: Lin, L
Wang, K
Zuo, W
Wang, M
Luo, J
Zhang, L 
Keywords: Human action and activity
RGB-depth analysis
Structured model
Deep learning
Issue Date: 2016
Publisher: Springer
Source: International journal of computer vision, 2016, v. 118, no. 2, p. 256-273 How to cite?
Journal: International journal of computer vision 
Abstract: Understanding human activity is very challenging even with the recently developed 3D/depth sensors. To solve this problem, this work investigates a novel deep structured model, which adaptively decomposes an activity instance into temporal parts using the convolutional neural networks. Our model advances the traditional deep learning approaches in two aspects. First, we incorporate latent temporal structure into the deep model, accounting for large temporal variations of diverse human activities. In particular, we utilize the latent variables to decompose the input activity into a number of temporally segmented sub-activities, and accordingly feed them into the parts (i.e. sub-networks) of the deep architecture. Second, we incorporate a radius-margin bound as a regularization term into our deep model, which effectively improves the generalization performance for classification. For model training, we propose a principled learning algorithm that iteratively (i) discovers the optimal latent variables (i.e. the ways of activity decomposition) for all training instances, (ii) updates the classifiers based on the generated features, and (iii) updates the parameters of multi-layer neural networks. In the experiments, our approach is validated on several complex scenarios for human activity recognition and demonstrates superior performances over other state-of-the-art approaches.
ISSN: 0920-5691 (print)
1573-1405 (online)
DOI: 10.1007/s11263-015-0876-z
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Aug 14, 2018


Last Week
Last month
Citations as of Aug 8, 2018

Page view(s)

Last Week
Last month
Citations as of Aug 12, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.