Fusing semantic aspects for image annotation and retrieval
文献类型：期刊论文
| 作者 | Li, Zhixin1,2; Shi, Zhiping1,3; Liu, Xi1; Li, Zhiqing1; Shi, Zhongzhi1 |
| 刊名 | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
 |
| 出版日期 | 2010-11-01 |
| 卷号 | 21期号:8页码:798-805 |
| 关键词 | Automatic image annotation Latent aspect model PLSA Adaptive asymmetric learning Image retrieval Semantic gap Visual feature Textual word |
| ISSN号 | 1047-3203 |
| DOI | 10.1016/j.jvcir.2010.06.004 |
| 英文摘要 | In this paper, we present an approach based on probabilistic latent semantic analysis (PLSA) to achieve the task of automatic image annotation and retrieval. In order to model training data precisely, each image is represented as a bag of visual words. Then a probabilistic framework is designed to capture semantic aspects from visual and textual modalities, respectively. Furthermore, an adaptive asymmetric learning algorithm is proposed to fuse these aspects. For each image document, the aspect distributions of different modalities are fused by multiplying different weights, which are determined by the visual representations of images. Consequently, the probabilistic framework can predict semantic annotation precisely for unseen images because it associates visual and textual modalities properly. We compare our approach with several state-of-the-art approaches on a standard Corel dataset. The experimental results show that our approach performs more effectively and accurately. (c) 2010 Elsevier Inc. All rights reserved. |
| 资助项目 | National Basic Research Priorities Programme[2007CB311004] ; National Science and Technology Support Plan[2006BAC08B06] ; National Natural Science Foundation of China[60775035] ; National Natural Science Foundation of China[60933004] ; National Natural Science Foundation of China[60903141] ; National Natural Science Foundation of China[60970088] ; National Natural Science Foundation of China[60903079] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000283827500004 |
| 出版者 | ACADEMIC PRESS INC ELSEVIER SCIENCE |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/12216]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Li, Zhixin |
| 作者单位 | 1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Guangxi Normal Univ, Coll Comp Sci & Informat Technol, Guilin 541004, Peoples R China 3.Capital Normal Univ, Informat Engn Coll, Beijing 100048, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Zhixin,Shi, Zhiping,Liu, Xi,et al. Fusing semantic aspects for image annotation and retrieval[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,2010,21(8):798-805. |
| APA | Li, Zhixin,Shi, Zhiping,Liu, Xi,Li, Zhiqing,&Shi, Zhongzhi.(2010).Fusing semantic aspects for image annotation and retrieval.JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,21(8),798-805. |
| MLA | Li, Zhixin,et al."Fusing semantic aspects for image annotation and retrieval".JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 21.8(2010):798-805. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。