Abstract | ||
---|---|---|
Scene images usually involve semantic correlations, particularly when considering large-scale image data sets. This paper proposes a novel generative image representation, correlated topic vector, to model such semantic correlations. Oriented from the correlated topic model, correlated topic vector intends to naturally utilize the correlations among topics, which are seldom considered in the conventional feature encoding, e.g., Fisher vector, but do exist in scene images. It is expected that the involvement of correlations can increase the discriminative capability of the learned generative model and consequently improve the recognition accuracy. Incorporated with the Fisher kernel method, correlated topic vector inherits the advantages of Fisher vector. The contributions to the topics of visual words have been further employed by incorporating the Fisher kernel framework to indicate the differences among scenes. Combined with the deep convolutional neural network (CNN) features and Gibbs sampling solution, correlated topic vector shows great potential when processing large-scale and complex scene image data sets. Experiments on two scene image data sets demonstrate that correlated topic vector improves significantly the deep CNN features, and outperforms existing Fisher kernel-based features. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/TIP.2017.2694320 | IEEE Trans. Image Processing |
Keywords | Field | DocType |
Semantics,Kernel,Correlation,Visualization,Image recognition,Feature extraction,Image coding | Computer science,Convolutional neural network,Artificial intelligence,Discriminative model,Fisher kernel,Kernel (linear algebra),Computer vision,Pattern recognition,Feature extraction,Topic model,Machine learning,Generative model,Visual Word | Journal |
Volume | Issue | ISSN |
26 | 7 | 1057-7149 |
Citations | PageRank | References |
0 | 0.34 | 42 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pengxu Wei | 1 | 9 | 2.87 |
Fei Qin | 2 | 12 | 4.76 |
Fang Wan | 3 | 21 | 3.44 |
Yi Zhu | 4 | 17 | 4.27 |
Jianbin Jiao | 5 | 367 | 32.61 |
Qixiang Ye | 6 | 913 | 64.51 |