Abstract | ||
---|---|---|
Most of the existing approaches for image annotation generally demand exactly labeled training data, which are often difficult to obtain. In this letter we present a novel model that utilizes the rich surrounding text of images to perform image annotation. Our work makes two main contributions. First, by integrating text analysis, words that describe the salient objects in images are extracted. Second, a new probabilistic topic model is built to jointly model image features, extracted words and surrounding text. Our model is demonstrated to be flexible enough to handle multi-modal features and provide better performance than the state-of-the-art annotation methods. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/LSP.2014.2375341 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
object extraction,word extraction,graphical models,image feature extraction,multimodal topic model,modal analysis,image annotation,text detection,feature extraction,image analysis,image retrieval,image text analysis,statistical learning,text analysis,probabilistic topic model,visualization,data models,computational modeling,probabilistic logic | Data modeling,Computer science,Image retrieval,Artificial intelligence,Natural language processing,Automatic image annotation,Annotation,Pattern recognition,Information retrieval,Feature (computer vision),Feature extraction,Topic model,Visual Word | Journal |
Volume | Issue | ISSN |
22 | 7 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 17 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jing Tian | 1 | 4 | 1.05 |
Yu Huang | 2 | 8 | 1.81 |
Zhi Guo | 3 | 8 | 0.82 |
Xiang Qi | 4 | 4 | 0.76 |
Ziyan Chen | 5 | 4 | 1.05 |
Tinglei Huang | 6 | 38 | 12.17 |