Abstract | ||
---|---|---|
•We exploit the distribution information of principal orientations of dataset by learning the projection matrix with trajectories on both spatial and temporal domains for extracting features informatively.•We exploit the residual information of projected features in the projection subspace by maximizing the residual value of features from principal orientations.•We consider the correlation between RGB channel and depth channel for RGB-D based action recognition and jointly learn the projection matrices on corresponding channels. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.patcog.2018.08.016 | Pattern Recognition |
Keywords | Field | DocType |
Action recognition,Unsupervised learning,Trajectories,Principal orientation,Residual value | Residual,Statistic,Pattern recognition,Action recognition,Communication channel,RGB color model,Artificial intelligence,Feature based,Quantization (signal processing),Discriminative model,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
86 | 1 | 0031-3203 |
Citations | PageRank | References |
0 | 0.34 | 38 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lei Chen | 1 | 128 | 53.70 |
Zhanjie Song | 2 | 11 | 3.93 |
Jiwen Lu | 3 | 3105 | 153.88 |
Jie Zhou | 4 | 2103 | 190.17 |