Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/81820
Title: Beyond Bag-of-Words: combining generative and discriminative models for scene categorization
Authors: Li, Zhen
Yap, Kim-Hui
Keywords: Bag-of-Words
Scene categorization
Issue Date: 2012
Source: Li, Z., & Yap, K.-H. (2014). Beyond Bag-of-Words: combining generative and discriminative models for scene categorization. Multimedia Tools and Applications, 71(3), 1033-1050.
Series/Report no.: Multimedia Tools and Applications
Abstract: This paper proposes an efficient framework for scene categorization by combining generative model and discriminative model. A state-of-the-art approach for scene categorization is the Bag-of-Words (BoW) framework. However, there exist many categories in scenes. Generally when a new category is considered, the codebook in BoW framework needs to be re-generated, which will involve exhaustive computation. In view of this, this paper tries to address the issue by designing a new framework with good scalability. When an additional category is considered, much lower computational cost is needed while the resulting image signatures are still discriminative. The image signatures for training discriminative model are carefully designed based on the generative model. The soft relevance value of the extracted image signatures are estimated by image signature space modeling and are incorporated in Fuzzy Support Vector Machine (FSVM). The effectiveness of the proposed method is validated on UIUC Scene-15 dataset and NTU-25 dataset, and it is shown to outperform other state-of-the-art approaches for scene categorization.
URI: https://hdl.handle.net/10356/81820
http://hdl.handle.net/10220/40967
ISSN: 1380-7501
DOI: 10.1007/s11042-012-1245-3
Schools: School of Electrical and Electronic Engineering 
Rights: © 2012 Springer Science+Business Media New York.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Page view(s) 50

490
Updated on Jun 17, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.