Supervised estimation methods are widely seen as being superior to semi and fully unsupervised methods. However, supervised methods crucially rely upon training sets that need to ...
Histograms of orientations and the statistics derived from them have proven to be effective image representations for various recognition tasks. In this work we attempt to improve...
Searching for images by using low-level visual features, such as color and texture, is known to be a powerful, yet imprecise, retrieval paradigm. The same is true if search relies...
The content of image archives changes rapidly. This makes the traditional separation of ontology development and image annotation steps no longer feasible. In this paper, we presen...
Learning to cope with domain change has been known
as a challenging problem in many real-world applications.
This paper proposes a novel and efficient approach, named
domain ada...
Yu-Gang Jiang, Jun Wang, Shih-Fu Chang, Chong-Wah ...