Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 39, Issue 11, Pages 2186-2200Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2016.2640292
Keywords
Heterogeneous features learning; RGB-D activity recognition; action recognition
Funding
- National Key Research and Development Program of China [2016YFB1001002, 2016YFB1001003]
- NSFC [61522115, 61573387, 61661130157, 61628212]
- Guangdong Natural Science Funds for Distinguished Young Scholar [S2013050014265]
- Guangdong Science and Technology Planning Project [2016A010102012]
- Guangdong Program for Support of Top-notch Young Professionals [2014TQ01X779]
Ask authors/readers for more resources
In this paper, we focus on heterogeneous features learning for RGB-D activity recognition. We find that features from different channels (RGB, depth) could share some similar hidden structures, and then propose a joint learning model to simultaneously explore the shared and feature-specific components as an instance of heterogeneous multi-task learning. The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets. To efficiently train the joint model, a three-step iterative optimization algorithm is proposed, followed by a simple inference model. Extensive experimental results on four activity datasets have demonstrated the efficacy of the proposed method. A new RGB-D activity dataset focusing on human-object interaction is further contributed, which presents more challenges for RGB-D activity benchmarking.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available