Abstract | ||
---|---|---|
In this paper, we present a novel two-layer video representation for human action recognition employing hierarchical group sparse encoding technique and spatio-temporal structure. In the first layer, a new sparse encoding method named locally consistent group sparse coding (LCGSC) is proposed to make full use of motion and appearance information of local features. LCGSC method not only encodes glo... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIP.2017.2788196 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Encoding,Image coding,Video sequences,Hidden Markov models,Visualization,Correlation,Layout | Computer vision,Abstraction,Pattern recognition,Neural coding,Visualization,Sparse approximation,Correlation,Artificial intelligence,Hidden Markov model,Location model,Mathematics,Encoding (memory) | Journal |
Volume | Issue | ISSN |
27 | 4 | 1057-7149 |
Citations | PageRank | References |
2 | 0.36 | 38 |
Authors | ||
5 |