Abstract | ||
---|---|---|
Local features have been widely used in computer vision tasks, e.g., human action recognition, but it tends to be an extremely challenging task to deal with large-scale local features of high dimensionality with redundant information. In this paper, we propose a novel fully supervised local descriptor learning algorithm called discriminative embedding method based on the image-to-class distance (I... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/TMM.2017.2700204 | IEEE Transactions on Multimedia |
Keywords | Field | DocType |
Kernel,Supervised learning,Image recognition,Manifolds,Feature extraction,Visualization,Measurement | Dimensionality reduction,Computer science,Artificial intelligence,Discriminative model,Kernel (linear algebra),Computer vision,Laplacian matrix,Embedding,Pattern recognition,Supervised learning,Feature extraction,Curse of dimensionality,Machine learning | Journal |
Volume | Issue | ISSN |
19 | 9 | 1520-9210 |
Citations | PageRank | References |
1 | 0.35 | 35 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiantong Zhen | 1 | 513 | 36.54 |
Feng Zheng | 2 | 369 | 31.93 |
Ling Shao | 3 | 5424 | 249.92 |
Xianbin Cao | 4 | 609 | 60.26 |
Dan Xu | 5 | 342 | 16.39 |