Loading...
Please wait, while we are loading the content...
Similar Documents
Pseudo Relevance Feedback Based on Iterative Probabilistic One-Class SVMs in Web Image Retrieval ⋆
| Content Provider | CiteSeerX |
|---|---|
| Author | He, Jingrui Li, Mingjing Li, Zhiwei Zhang, Hong-Jiang Tong, Hanghang Zhang, Changshui |
| Abstract | Abstract. To improve the precision of top-ranked images returned by a web image search engine, we propose in this paper a novel pseudo relevance feedback method named iterative probabilistic one-class SVMs to re-rank the retrieved images. By assuming that most top-ranked images are relevant to the query, we iteratively train one-class SVMs, and convert the outputs to probabilities so as to combine the decision from different image representation. The effectiveness of our method is validated by systematic experiments even if the assumption is not well satisfied. 1 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Iterative Probabilistic One-class Svms Pseudo Relevance Feedback Web Image Retrieval Top-ranked Image Web Image Search Engine One-class Svms Novel Pseudo Relevance Feedback Method Different Image Representation Systematic Experiment Retrieved Image |
| Content Type | Text |
| Resource Type | Article |
