Incremental Codebook Adaptation for Visual Representation and Categorization
文献类型：期刊论文
| 作者 | Zhang, Chunjie1 ; Cheng, Jian2; Tian, Qi3
|
| 刊名 | IEEE TRANSACTIONS ON CYBERNETICS
 |
| 出版日期 | 2018-07-01 |
| 卷号 | 48期号:7页码:2012-2023 |
| 关键词 | Codebook learning low-rank sparse coding visual representation |
| ISSN号 | 2168-2267 |
| DOI | 10.1109/TCYB.2017.2726079 |
| 通讯作者 | Zhang, Chunjie(chunjie.zhang@ia.ac.cn) |
| 英文摘要 | The bag-of-visual-words model is widely used for visual content analysis. For visual data, the codebook plays an important role for efficient representation. However, the codebook has to be relearned with the changes of training images. Once the codebook is changed, the encoding parameters of local features have to be recomputed. To alleviate this problem, in this paper, we propose an incremental codebook adaptation method for efficient visual representation. Instead of learning a new codebook, we gradually adapt a prelearned codebook using new images in an incremental way. To make use of the prelearned codebook, we try to make changes to the prelearned codebook with sparsity constraint and low-rank correlation. Besides, we also encode visually similar local features within a neighborhood to take advantage of locality information and ensure the encoded parameters are consistent. To evaluate the effectiveness of the proposed method, we apply the proposed method for categorization tasks on several public image datasets. Experimental results prove the effectiveness and usefulness of the proposed method over other codebook-based methods. |
| WOS关键词 | VIEW ACTION RECOGNITION ; IMAGE CLASSIFICATION ; LOW-RANK ; SPARSE REPRESENTATION ; DOMAIN ADAPTATION ; SCENE CATEGORIES ; DICTIONARY ; KERNEL ; DECOMPOSITION ; INTEGRATION |
| 资助项目 | National Natural Science Foundation of China[61303154] ; National Natural Science Foundation of China[61332016] ; Scientific Research Key Program of Beijing Municipal Commission of Education[KZ201610005012] ; National Science Foundation of China[61429201] ; ARO[W911NF-15-1-0290] ; Faculty Research Gift Awards by NEC Laboratories of America and Blippar |
| WOS研究方向 | Automation & Control Systems ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000435342100006 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Scientific Research Key Program of Beijing Municipal Commission of Education ; National Science Foundation of China ; ARO ; Faculty Research Gift Awards by NEC Laboratories of America and Blippar |
| 源URL | [http://ir.ia.ac.cn/handle/173211/15319]  |
| 专题 | 类脑芯片与系统研究 |
| 通讯作者 | Zhang, Chunjie |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 3.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA |
| 推荐引用方式 GB/T 7714 | Zhang, Chunjie,Cheng, Jian,Tian, Qi. Incremental Codebook Adaptation for Visual Representation and Categorization[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(7):2012-2023. |
| APA | Zhang, Chunjie,Cheng, Jian,&Tian, Qi.(2018).Incremental Codebook Adaptation for Visual Representation and Categorization.IEEE TRANSACTIONS ON CYBERNETICS,48(7),2012-2023. |
| MLA | Zhang, Chunjie,et al."Incremental Codebook Adaptation for Visual Representation and Categorization".IEEE TRANSACTIONS ON CYBERNETICS 48.7(2018):2012-2023. |
入库方式： OAI收割
来源：自动化研究所
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。