Abstract | ||
---|---|---|
With the rapid development of bag-of-visual-word model and its wide-spread applications in various computer vision problems such as visual recognition, image retrieval tasks, etc., fast visual word assignment becomes increasingly important, especially for some on-line services and large scale settings. The conventional approximate nearest neighbor mapping techniques purely consider the distribution of image local descriptors in the visual feature space and perform the mapping process independently for each descriptor. In this paper, we propose to involve the spatial correlation information to boost the efficiency of feature quantization. The visual words that frequently co-occur in the same local region of a large number of images are considered as spatial neighborhoods, which can be leveraged to boost the approximate mapping of neighbored local descriptors. Experimental results on a well-known image retrieval dataset demonstrate that, the proposed method is capable of improving the efficiency and precision of visual word assignment. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICME.2011.6011893 | ICME |
Keywords | Field | DocType |
approximate mapping,mapping technique,visual word quantization,image local descriptors,visual word,visual words,local region,spatial neighborhood,visual word assignment,image retrieval,mapping process,image retrieval task,visual recognition,visual feature space,spatial correlation,visualization,indexes,mutual information,correlation,artificial neural networks,quantization | k-nearest neighbors algorithm,Computer vision,Feature vector,Pattern recognition,Visualization,Computer science,Image retrieval,Mutual information,Boosting (machine learning),Artificial intelligence,Quantization (signal processing),Visual Word | Conference |
ISSN | ISBN | Citations |
1945-7871 E-ISBN : 978-1-61284-349-0 | 978-1-61284-349-0 | 2 |
PageRank | References | Authors |
0.39 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ruixin Xu | 1 | 9 | 0.82 |
Miaojing Shi | 2 | 186 | 11.27 |
Bo Geng | 3 | 604 | 22.44 |
Chao Xu | 4 | 1327 | 62.65 |