![](/images/graphics-bg.png)
Semantic middleware : multi-layer abstract semantics inference for object categorization
Joint Authors
Zhao, Wei
Ye, Zhipeng
Tang, Xianglong
Liu, Peng
Source
The International Arab Journal of Information Technology
Issue
Vol. 13, Issue 6A(s) (31 Dec. 2016), pp.938-943, 6 p.
Publisher
Publication Date
2016-12-31
Country of Publication
Jordan
No. of Pages
6
Main Subjects
Information Technology and Computer Science
Abstract EN
In this paper, we present a hierarchical model, named as Multi-layer Abstract Semantics Inference (MASI), based on Bag-of-Visual-Words (BoVW) to solve the problem of universal image categorization, including typical and zero-shot image categorization.
An abstract hierarchical semantics learning method is proposed in the training step by extracting and selecting abstract visual words in a bottom-up way to train abstract semantic classifiers.
For a testing image, its category is estimated layer-by-layer from top to bottom according to its corresponding hierarchical categories.
Experimental results on popular image datasets have shown that the proposed method achieves better performance compared with traditional learning methods.
American Psychological Association (APA)
Liu, Peng& Ye, Zhipeng& Zhao, Wei& Tang, Xianglong. 2016. Semantic middleware : multi-layer abstract semantics inference for object categorization. The International Arab Journal of Information Technology،Vol. 13, no. 6A(s), pp.938-943.
https://search.emarefa.net/detail/BIM-792146
Modern Language Association (MLA)
Liu, Peng…[et al.]. Semantic middleware : multi-layer abstract semantics inference for object categorization. The International Arab Journal of Information Technology Vol. 13, no. 6A (Special issue) (Dec. 2016), pp.938-943.
https://search.emarefa.net/detail/BIM-792146
American Medical Association (AMA)
Liu, Peng& Ye, Zhipeng& Zhao, Wei& Tang, Xianglong. Semantic middleware : multi-layer abstract semantics inference for object categorization. The International Arab Journal of Information Technology. 2016. Vol. 13, no. 6A(s), pp.938-943.
https://search.emarefa.net/detail/BIM-792146
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 942-943
Record ID
BIM-792146