Abstract | ||
---|---|---|
We address the problem of instance classification: our goal is to annotate images with tags corresponding to objects classes which exhibit small intra-class variations such as logos, products or landmarks. We propose a novel algorithm for the selection of class-specific prototypes which are used in a voting-based classification scheme. We show significant improvements over two state-of-the-art methods, namely the Fisher vector and Hamming Embedding, on two challenging methods of logos and vehicles. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2578726.2578786 | ICMR |
Keywords | Field | DocType |
novel algorithm,significant improvement,prototype selection,class-specific prototype,instance classification,hamming embedding,exhibit small intra-class variation,challenging method,voting-based classification scheme,fisher vector,objects class,feature selection,computer vision,image classification | Hamming code,Embedding,Fisher vector,Voting,Feature selection,Pattern recognition,Computer science,Classification scheme,Logos Bible Software,Artificial intelligence,Contextual image classification,Machine learning | Conference |
Citations | PageRank | References |
9 | 0.55 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Josip Krapac | 1 | 199 | 12.31 |
Florent Perronnin | 2 | 5448 | 291.48 |
Teddy Furon | 3 | 660 | 55.04 |
Hervé Jégou | 4 | 5682 | 247.98 |