Abstract | ||
---|---|---|
Automatically annotating words for images is a key to semantic-level image retrieval. Recently, several embedding learning based methods achieve good performance in this task which inspires this paper. Here we propose a novel word embedding model in which both images and words can be represented in the same embedding space. The embedding space is learnt in a discriminative nearest neighbor manner such that the annotation information could be propagated among neighbors. In order to accelerate model learning and testing, approximate-nearest-neighbor search is performed, and word embedding space is learnt in a stochastic manner. The experimental results demonstrate the effectiveness of the proposed method. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICTAI.2012.44 | ICTAI |
Keywords | Field | DocType |
automatically annotating word,image representation,approximate-nearest-neighbor search,neighbor manner,word embedding space,embedding learning,novel word,automatic image annotation,semantic level image retrieval,image annotation,word embedding model,automatic words annotation,annotation information,approximate nearest neighbor search,image retrieval,good performance,discriminative nearest neighbor,stochastic manner,nearest neighbor,natural language processing,word embedding learning,embedding space | Computer science,Image retrieval,Artificial intelligence,Natural language processing,Word embedding,Discriminative model,k-nearest neighbors algorithm,Automatic image annotation,Embedding,Pattern recognition,Visualization,Feature extraction,Machine learning | Conference |
Volume | ISSN | ISBN |
1 | 1082-3409 | 978-1-4799-0227-9 |
Citations | PageRank | References |
0 | 0.34 | 20 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qi Chen | 1 | 2 | 0.71 |
Andy M. Yip | 2 | 232 | 20.65 |
Chew Lim Tan | 3 | 4484 | 284.26 |