Name
Abstract | ||
|---|---|---|
Discriminative learning of sparse-code based dictionaries tends to be inherently unstable. We show that using a discriminative version of the deviation function to learn such dictionaries leads to a more stable formulation that can handle the reconstruction/discrimination trade-off in a principled manner. Results on Graz02 and UCF Sports datasets validate the proposed formulation. |
Year | Venue | Keywords |
|---|---|---|
2012 | ICPR | dictionaries,image coding,learning (artificial intelligence),object recognition,vocabulary,Graz02 Sports dataset,UCF Sports dataset,bag-of-words,deviation function,discrimination trade-off,discriminative deviation,object recognition,reconstruction trade-off,sparse-code based dictionaries,stable discriminative dictionary learning,vocabulary generalization |
Field | DocType | ISSN |
Dictionary learning,Pattern recognition,Computer science,Image coding,Speech recognition,Artificial intelligence,Vocabulary,Discriminative model,Discriminative learning,Cognitive neuroscience of visual object recognition | Conference | 1051-4651 |
Citations | PageRank | References |
2 | 0.38 | 7 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nazar Khan | 1 | 15 | 6.38 |
| Marshall F. Tappen | 2 | 1901 | 89.34 |