Beyond Bag-of-Words: combining generative and discriminative models for scene categorization
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 consi...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/81820 http://hdl.handle.net/10220/40967 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-81820 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-818202020-03-07T13:56:08Z Beyond Bag-of-Words: combining generative and discriminative models for scene categorization Li, Zhen Yap, Kim-Hui School of Electrical and Electronic Engineering Bag-of-Words Scene categorization 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. ASTAR (Agency for Sci., Tech. and Research, S’pore) 2016-07-19T05:51:25Z 2019-12-06T14:40:58Z 2016-07-19T05:51:25Z 2019-12-06T14:40:58Z 2012 Journal Article 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. 1380-7501 https://hdl.handle.net/10356/81820 http://hdl.handle.net/10220/40967 10.1007/s11042-012-1245-3 en Multimedia Tools and Applications © 2012 Springer Science+Business Media New York. |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Bag-of-Words Scene categorization |
spellingShingle |
Bag-of-Words Scene categorization Li, Zhen Yap, Kim-Hui Beyond Bag-of-Words: combining generative and discriminative models for scene categorization |
description |
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. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Li, Zhen Yap, Kim-Hui |
format |
Article |
author |
Li, Zhen Yap, Kim-Hui |
author_sort |
Li, Zhen |
title |
Beyond Bag-of-Words: combining generative and discriminative models for scene categorization |
title_short |
Beyond Bag-of-Words: combining generative and discriminative models for scene categorization |
title_full |
Beyond Bag-of-Words: combining generative and discriminative models for scene categorization |
title_fullStr |
Beyond Bag-of-Words: combining generative and discriminative models for scene categorization |
title_full_unstemmed |
Beyond Bag-of-Words: combining generative and discriminative models for scene categorization |
title_sort |
beyond bag-of-words: combining generative and discriminative models for scene categorization |
publishDate |
2016 |
url |
https://hdl.handle.net/10356/81820 http://hdl.handle.net/10220/40967 |
_version_ |
1681037310102077440 |