Name
Abstract | ||
|---|---|---|
Retrieving images for an arbitrary user query, provided in textual form, is a challenging problem. A recently proposed method addresses this by constructing a visual classifier with images returned by an internet image search engine, based on the user query, as positive images while using a fixed pool of negative images. However, in practice, not all the images obtained from internet image search are always pertinent to the query; some might contain abstract or artistic representation of the content and some might have artifacts. Such images degrade the performance of on-the-fly constructed classifier. We propose a method for improving the performance of on-the-fly classifiers by using transfer learning via attributes. We first map the textual query to a set of known attributes and then use those attributes to prune the set of images downloaded from the internet. This pruning step can be seen as zero-shot learning of the visual classifier for the textual user query, which transfers knowledge from the attribute domain to the query domain. We also use the attributes along with the on-the-fly classifier to score the database images and obtain a hybrid ranking. We show interesting qualitative results and demonstrate by experiments with standard datasets that the proposed method improves upon the baseline on-the-fly classification system. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/WACV.2014.6836097 | Applications of Computer Vision |
Keywords | Field | DocType |
Internet,image classification,image retrieval,learning (artificial intelligence),search engines,Internet image search engine,arbitrary user query,hybrid ranking,image retrieval,improved on-the-fly classification,negative images,on-the-fly constructed classifier,textual form,textual user query,transfer learning,visual classifier,zero-shot learning | Computer science,Transfer of learning,Web query classification,Artificial intelligence,Classifier (linguistics),The Internet,Attribute domain,Computer vision,Web search query,Information retrieval,Pattern recognition,Visualization,Support vector machine | Conference |
ISSN | Citations | PageRank |
2472-6737 | 2 | 0.35 |
References | Authors | |
19 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Praveen Kulkarni | 1 | 2 | 0.35 |
| Gaurav Sharma | 2 | 64 | 14.68 |
| Joaquin Zepeda | 3 | 19 | 1.81 |
| Louis Chevallier | 4 | 2 | 2.38 |