Abstract | ||
---|---|---|
•The key contribution is domain adaptation for weakly supervised hand pose recovery. Both the training samples and testing samples are represented in a unified space and aligning parameters are computed in this space. These parameters are used to align the testing samples to the domain of training samples.•The second contribution is domain adaptation with low-rank representation. Low-rank representation is sparse and the distributions of training samples and testing samples can be observed clearly. In this way, the process of alignment can be achieved in low-rank feature space.•The third contribution is the mapping between 2D depth images and 3D hand poses are computed by a neural network with 2 hidden layers. In this way, their relationship is described on a non-linear manner. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.sigpro.2017.07.032 | Signal Processing |
Keywords | Field | DocType |
Human hand pose recovery,Neural network,Domain adaptation,Low-rank representation | Feature vector,Pattern recognition,Domain adaptation,Feature (computer vision),Artificial intelligence,Deep learning,Labeled data,Artificial neural network,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
142 | C | 0165-1684 |
Citations | PageRank | References |
1 | 0.35 | 44 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chaoqun Hong | 1 | 324 | 13.19 |
Zhiqiang Zeng | 2 | 139 | 16.35 |
Rongsheng Xie | 3 | 1 | 0.35 |
Weiwei Zhuang | 4 | 1 | 0.35 |
Xiaodong Wang | 5 | 35 | 5.19 |