Abstract | ||
---|---|---|
This paper addresses the problem of recognizing human actions from RGB-D videos. A discriminative relational feature learning method is proposed for fusing heterogeneous RGB and depth modalities, and classifying the actions in RGB-D sequences. Our method factorizes the feature matrix of each modality, and enforces the same semantics for them in order to learn shared features from multimodal data. ... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TIP.2016.2556940 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Feature extraction,Testing,Semantics,Correlation,Training,Data mining,Videos | Modalities,Data set,Hinge loss,Artificial intelligence,RGB color model,Coordinate descent,Discriminative model,Computer vision,Pattern recognition,Feature learning,Machine learning,Semantics,Mathematics | Journal |
Volume | Issue | ISSN |
25 | 6 | 1057-7149 |
Citations | PageRank | References |
5 | 0.41 | 28 |
Authors | ||
2 |