Loading...
Please wait, while we are loading the content...
Semantics-preserving bag-of-words models and applications (1908)
| Content Provider | CiteSeerX |
|---|---|
| Author | Wu, Lei Hoi, Steven C. H. Yu, Nenghai |
| Abstract | The Bag-of-Words (BoW) model is a promising image representation for annotation. One critical limitation of existing BoW models is the semantic loss during the codebook generation process, in which BoW simply clusters visual words in Euclidian space. However, distance between two visual words in Euclidean space does not necessarily reflect the semantic distance between the two concepts, due to the semantic gap between low-level features and high-level semantics. In this paper, we propose a novel scheme for learning a codebook such that semantically related features will be mapped to the same visual word. In particular, we consider the distance between semantically identical features as a measurement of the semantic gap, and attempt to learn an optimized codebook by minimizing this gap. We refer to such a new codebook method as Semantics-Preserving Codebook (SPC) and the corresponding model as Semantics-Preserving Bagof-Words model (SPBoW). This novel model generates codebook |
| File Format | |
| Journal | IEEE Trans. on Image Processing |
| Language | English |
| Publisher Date | 1908-01-01 |
| Access Restriction | Open |
| Subject Keyword | Semantics-preserving Bag-of-words Model Visual Word Semantic Gap Low-level Feature Novel Model Generates High-level Semantics Novel Scheme Semantic Loss Codebook Generation Process Critical Limitation Optimized Codebook New Codebook Method Semantic Distance Promising Image Representation Corresponding Model Identical Feature Semantics-preserving Codebook Semantics-preserving Bagof-words Model Euclidian Space Bow Model Euclidean Space |
| Content Type | Text |
| Resource Type | Article |
