arrow
返回

Semantic-aware visual scene representation

delete2022-08-30
delete4
PRE
AI
M
Mohammad Javad Parseh
M
Mohammad Rahmanimanesh *
K
Keshavarzi, Parviz
Z
Zohreh Azimifar
DOI:10.1007/s13735-022-00246-5delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Scene classification is a mature and active computer vision task, due to the inherent ambiguity. The scene classification task aims to classify the visual scene images in predefined categories based on the ambient content, objects and the layout of the images. Inspired by human visual scene understanding, the visual scenes can be divided into two categories: (1) Object-based scenes that consist of the scene-specific objects and can be understood with those objects. (2) Layout-based scenes that are understandable based on the layout and the ambient content of the scene images. Scene-specific objects semantically help to understand object-based scenes, whereas the layout and the ambient content are effective in understanding layout-based scenes by representing the visual appearance of the scene images. Hence, one of the main challenges in scene classification is to create a discriminative representation that can provide a high-level perception of visual scenes. Accordingly, we have presented a discriminative hybrid representation of visual scenes, in which semantic features extracted from scene-specific objects are fused with visual features extracted from a deep CNN. The proposed scene representation method is used for the scene classification task and is applied to three benchmark scene datasets including: MIT67, SUN397, and UIUC Sports. Moreover, a new scene dataset, called Scene40, has been introduced, and also, the results of our proposed method have been presented on it. Experimental results show that our proposed method has achieved remarkable performance in the scene classification task and has outperformed the state-of-the-art methods.
Keyword:
Scene representation
Scene-specific object
Semantic feature
Deep visual feature

期刊

International Journal of Multimedia Information Retrieval 封面图
International Journal of Multimedia Information Retrieval
IF:
2.9
论文数:
280
被引数:
866

机构

S
semnan university
学者数:
3.4K
论文数: 3.2K
被引数: 2
S
Shiraz University
学者数:
8.1K
论文数: 7.5K
被引数: 7.4K
引用论文

引用论文

Social science research on HIV in Vietnam: A critical review and future directions
err2013-07-26
err0
errOAAI
errAmy Dao; Jennifer S. Hirsch; Le Minh Giang; Richard G. Parker
err分享
err收藏
Stearoyl-CoA Desaturase-1 (SCD1) Augments Saturated Fatty Acid-Induced Lipid Accumulation and Inhibits Apoptosis in Cardiac Myocytes
err2012-03-08
err0
errOAAI
errHiroki Matsui; Tomoyuki Yokoyama; Kenichi Sekiguchi; Daisuke Iijima; Hiroaki Sunaga; Moeno Maniwa; Manabu Ueno; Tatsuya Iso; Masashi Arai; Masahiko Kurabayashi
err分享
err收藏
Learning visual features for relational CBIR
err2019-09-14
err10
PREAI
errMessina, Nicola; Amato, Giuseppe; Carrara, Fabio; Falchi, Fabrizio; Gennaro, Claudio
err分享
err收藏
A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification
err2016-10-01
err59
errOAAI
errHayat, Munawar; Khan, Salman H.; Bennamoun, Mohammed; An, Senjian
err分享
err收藏
Selective Search for Object Recognition
err2013-04-02
err3.9K
PREAI
errUijlings, J. R. R.; van de Sande, K. E. A.; Gevers, T.; Smeulders, A. W. M.
err分享
err收藏
学者 查看更多内容