78 search results - page 15 / 16 » Improving Automatic Image Annotation Based on Word Co-occurr... |
MIR
2005
ACM
13 years 11 months ago
2005
ACM
In this paper, we propose a multimodal Web image retrieval technique based on multi-graph enabled active learning. The main goal is to leverage the heterogeneous data on the Web t...
ECCV
2006
Springer
14 years 8 months ago
2006
Springer
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...
MICAI
2010
Springer
13 years 4 months ago
2010
Springer
We argue for that taking into account semantic relations between words in the text can improve information retrieval performance. We implemented the process of information retrieva...
PAMI
2012
11 years 8 months ago
2012
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
CVPR
2008
IEEE
14 years 8 months ago
2008
IEEE
Objects in the world can be arranged into a hierarchy based on their semantic meaning (e.g. organism ? animal ? feline ? cat). What about defining a hierarchy based on the visual ...