Semantic Middleware: Multi-Layer Abstract Semantics
Inference for Object Categorization
Peng Liu,
Zhipeng Ye, Wei Zhao and Xianglong Tang School of Computer Science and
Technology, Harbin Institute of Technology, China
Abstract: 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.
Keywords: Image categorization, zero-shot learning, semantic
abstraction, BoVW.
Received November 11, 2014; accepted December 21, 2015
