Abstract | ||
---|---|---|
•Our CMFL model jointly learns shared-specific features and action classifiers.•The proposed RSTPF features extract dynamic local patterns around each human joint.•The CMFL model enables the features to be optimized for classification.•The CMFL performs well even if one or two modalities are missing in the testing stage.•A max-margin framework is introduced to fuse skeleton, depth and RGB data. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.jvcir.2019.02.013 | Journal of Visual Communication and Image Representation |
Keywords | Field | DocType |
RGB-D action recognition,Multimodal data,Max-margin learning framework,Supervised matrix factorization | Modalities,Computer vision,Pattern recognition,Matrix (mathematics),Action recognition,Artificial intelligence,Optimization algorithm,Pyramid,RGB color model,Fuse (electrical),Mathematics,Feature learning | Journal |
Volume | ISSN | Citations |
59 | 1047-3203 | 1 |
PageRank | References | Authors |
0.35 | 37 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Kong | 1 | 111 | 18.94 |
Tianshan Liu | 2 | 9 | 4.27 |
Min Jiang | 3 | 39 | 13.65 |