Name
Title | ||
|---|---|---|
Latent space mapping for generation of object elements with corresponding data annotation. |
Abstract | ||
|---|---|---|
•Deep neural Generators are giving impressive results in learning data distribution.•Knowing the latent space for a perfect generator is equal to knowing the data.•The latent space can be mapped to any aspect of the database.•Aspect mapping is accomplished by small networks and minimizing mean square error. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.patrec.2018.10.025 | Pattern Recognition Letters |
Keywords | Field | DocType |
Generative models,Latent space mapping,Deep neural networks | Spatial analysis,Computer vision,Use case,Pattern recognition,Space mapping,Segmentation,Mean squared error,Artificial intelligence,Generative grammar,Artificial neural network,Landmark,Mathematics | Journal |
Volume | ISSN | Citations |
116 | 0167-8655 | 0 |
PageRank | References | Authors |
0.34 | 9 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| S. Bazrafkan | 1 | 58 | 5.44 |
| Hossein Javidnia | 2 | 10 | 4.71 |
| P. M. Corcoran | 3 | 414 | 82.56 |