Name
Abstract | ||
|---|---|---|
This paper presents the algorithms and results of our participation to the image annotation task of ImageCLEFmed 2007. We proposed a multi-cue approach where images are represented both by global and local descriptors. These cues are combined following two SVM-based strategies. The first algorithm, called Discriminative Accumulation Scheme (DAS), trains an SVM for each feature, and considers as output of each classifier the distance from the separating hyperplane. The final decision is taken on a linear combination of these distances. The second algorithm, that we call Multi Cue Kernel (MCK), uses a new Mercer kernel which can accept as input different features while keeping them separated. The DAS algorithm obtained a score of 29.9, which ranked fifth among all submissions. The MCK algorithm with the one-vs-all and with the one-vs-one multiclass extensions of SVM scored respectively 26.85 and 27.54. These runs ranked first and second among all submissions. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-85760-0_72 | Advances in Multilingual and Multimodal Information Retrieval |
Keywords | Field | DocType |
cue integration,linear combination,svm-based strategy,final decision,multi cue kernel,input different feature,mck algorithm,local descriptors,das algorithm,image annotation task,medical image,discriminative accumulation scheme,image annotation | Linear combination,Computer science,Artificial intelligence,Hyperplane,Classifier (linguistics),Discriminative model,Kernel (linear algebra),Automatic image annotation,Ranking,Information retrieval,Pattern recognition,Support vector machine,Machine learning | Conference |
Volume | ISSN | Citations |
5152 | 0302-9743 | 1 |
PageRank | References | Authors |
0.38 | 8 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tatiana Tommasi | 1 | 502 | 29.31 |
| Francesco Orabona | 2 | 881 | 51.44 |
| Barbara Caputo | 3 | 3298 | 201.26 |