| Title: | Heterogeneous Metric Learning for Cross-Modal Multimedia Retrieval |
| Author: | Deng, Jun
; Du, Liang
; Shen, Yi-Dong
|
| Conference Name: | 14th International Conference on Web Information Systems Engineering (WISE)
|
| Conference Date: | OCT 13-15, 2013
|
| Issued Date: | 2013
|
| Conference Place: | Nanjing, PEOPLES R CHINA
|
| Keyword: | Metric Learning
; Heterogeneous Spaces
; Multimedia
|
| Publish Place: | SPRINGER-VERLAG BERLIN
|
| Indexed Type: | CPCI
|
| ISSN: | 0302-9743
|
| ISBN: | 978-3-642-41230-1; 978-3-642-41229-5
|
| Department: | [Deng, Jun; Du, Liang; Shen, Yi-Dong] Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China.
|
| Abstract: | Due to the massive explosion of multimedia content on the web, users demand a new type of information retrieval, called cross-modal multimedia retrieval where users submit queries of one media type and get results of various other media types. Performing effective retrieval of heterogeneous multimedia content brings new challenges. One essential aspect of these challenges is to learn a heterogeneous metric between different types of multimedia objects. In this paper, we propose a Bayesian personalized ranking based heterogeneous metric learning (BPRHML) algorithm, which optimizes for correctly ranking the retrieval results. It uses pairwise preference constraints as training data and explicitly optimizes for preserving these constraints. To further encouraging the smoothness of learning results, we integrate graph regularization with Bayesian personalized ranking. The experimental results on two publicly available datasets show the effectiveness of our method. |
| English Abstract: | Due to the massive explosion of multimedia content on the web, users demand a new type of information retrieval, called cross-modal multimedia retrieval where users submit queries of one media type and get results of various other media types. Performing effective retrieval of heterogeneous multimedia content brings new challenges. One essential aspect of these challenges is to learn a heterogeneous metric between different types of multimedia objects. In this paper, we propose a Bayesian personalized ranking based heterogeneous metric learning (BPRHML) algorithm, which optimizes for correctly ranking the retrieval results. It uses pairwise preference constraints as training data and explicitly optimizes for preserving these constraints. To further encouraging the smoothness of learning results, we integrate graph regularization with Bayesian personalized ranking. The experimental results on two publicly available datasets show the effectiveness of our method. |
| Language: | 英语
|
| Content Type: | 会议论文
|
| URI: | http://ir.iscas.ac.cn/handle/311060/16527
|
| Appears in Collections: | 软件所图书馆_会议论文
|
|
There are no files associated with this item.
|
| Recommended Citation: | |
Deng, Jun,Du, Liang,Shen, Yi-Dong. Heterogeneous Metric Learning for Cross-Modal Multimedia Retrieval[C]. 见:14th International Conference on Web Information Systems Engineering (WISE). Nanjing, PEOPLES R CHINA. OCT 13-15, 2013.
|
|
|
