Abstract | ||
---|---|---|
In this paper we aim to employ deep learning to enhance SBIR via deep discriminative representation. Our main contributions focus on: 1) The deep discriminative representation is established to bridge both the visual appearance gap and the semantic gap between sketches and images; 2) The deep learning pattern is applied to our SBIR model through training on our transformed sketch-like images to overcome the rarity of training sketches. Our experiments on a large number of public sketch and image data have obtained very positive results. |
Year | DOI | Venue |
---|---|---|
2016 | 10.3233/978-1-61499-672-9-1626 | Frontiers in Artificial Intelligence and Applications |
Field | DocType | Volume |
Information retrieval,Computer science,Semantic gap,Image retrieval,Natural language processing,Artificial intelligence,Deep learning,Discriminative model,Machine learning,Visual appearance,Visual Word,Sketch | Conference | 285 |
ISSN | Citations | PageRank |
0922-6389 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huang Fei | 1 | 17 | 4.28 |
Yong Cheng | 2 | 21 | 5.17 |
Cheng Jin | 3 | 78 | 14.92 |
Yuejie Zhang | 4 | 127 | 25.82 |
Tao Zhang | 5 | 422 | 100.57 |