Abstract | ||
---|---|---|
•We construct a large scale image annotation model AIACNN by modifying the CaffeNet model.•The Multitask Voting (MV) method we proposed can select the original dataset and improve the accuracy of annotation to a certain extent.•The MV method can also be applied to achieving the adaptive label by combining the Naive Bayesian probability model. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.jvcir.2017.07.004 | Journal of Visual Communication and Image Representation |
Keywords | Field | DocType |
Deep learning,Automatic image annotation,Adaptive label,Multitasking,Convolutional neural network | Convolutional neural network,Computer science,Image retrieval,Training effect,Artificial intelligence,Deep learning,Computer vision,Automatic image annotation,Annotation,Voting,Pattern recognition,Human multitasking,Machine learning | Journal |
Volume | ISSN | Citations |
49 | 1047-3203 | 3 |
PageRank | References | Authors |
0.36 | 19 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ronggui Wang | 1 | 44 | 10.06 |
Yunfei Xie | 2 | 3 | 0.36 |
Juan Yang | 3 | 40 | 10.74 |
Lixia Xue | 4 | 8 | 4.56 |
Min Hu | 5 | 31 | 12.64 |
Qingyang Zhang | 6 | 3 | 0.36 |