Name
Abstract | ||
|---|---|---|
Graph-based similarity ranking plays a key role in improving image retrieval performance. Its current trend is to fuse the ranking results from multiple feature sets, including textual feature, visual feature and query log feature, to elevate the retrieval effectiveness. The primary challenge is how to effectively exploit the complementary properties of different features. Another tough issue is the highly noisy features contributed by users, such as textual tags and query logs, which makes the exploration of such complementary properties difficult. This paper proposes a Multi-view Manifold Ranking M2R framework, in which multiple graphs built on different features are integrated to simultaneously encode the similarity ranking. To deal with the high noise issue inherent in the user-contributed features, a data cleaning solution based on visual-neighbor voting is embedded into M2R, thus called Robust M2R RM2R. Experimental results show that the proposed method significantly outperforms the existing approaches, especially when the user-contributed features are highly noisy. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-31750-2_8 | PAKDD |
Keywords | Field | DocType |
Image retrieval,Multi-view learning,Manifold ranking,Data cleaning | Data mining,ENCODE,Ranking SVM,Ranking,Computer science,Image retrieval,Exploit,Ranking (information retrieval),Artificial intelligence,Fuse (electrical),Machine learning,Visual Word | Conference |
Volume | ISSN | Citations |
9652 | 0302-9743 | 2 |
PageRank | References | Authors |
0.37 | 23 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun Wu | 1 | 125 | 15.66 |
| Jianbo Yuan | 2 | 80 | 5.09 |
| Jiebo Luo | 3 | 6314 | 374.00 |