Name
Abstract | ||
|---|---|---|
Visual concept detection in images has been a challenging task for many years. The recently proposed MIRFLICKR-25000 dataset has set the standards even higher as the wide variety of images and annotations require new techniques to tackle the visual concept detection problem. We propose the use of the recently introduced MOD salient points for subimage visual concept detection. These points are located at regions within an image that are distinctive with respect to the features that are selected for subimage classification. We also introduce the notion of Minimum Explanation Complexity (MEC), where the complexity of classifiers is reduced to a simpler but equally effective form whenever possible. Our experiments on the MIRFLICKR-25000 dataset show that MOD based concept detectors outperform SIFT based features. We also show that a neural network classifier based on the MEC notion, outperforms a standard SVM classifier. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1145/1743384.1743479 | Multimedia Information Retrieval |
Keywords | Field | DocType |
subimage visual concept detection,minimum explanation complexity,mirflickr-25000 dataset show,mod salient point,neural network classifier,visual concept detection,standard svm classifier,mirflickr-25000 dataset,visual concept detection problem,concept detector,mec notion,feature extraction | Scale-invariant feature transform,Mod,Neural network classifier,Pattern recognition,Computer science,Feature extraction,Artificial intelligence,Svm classifier,Machine learning,Salient | Conference |
Citations | PageRank | References |
2 | 0.42 | 18 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ard Oerlemans | 1 | 83 | 6.20 |
| Michael S. Lew | 2 | 2742 | 166.02 |