Sparse coding which encodes the original signal in a sparse signal space, has shown its state-of-the-art performance in the visual codebook generation and feature quantization pro...
Currently, the bag of visual words (BOW) representation has received wide applications in object categorization. However, the BOW representation ignores the dependency relationshi...
This paper shows how semantic attribute features can be used to improve object classification performance. The semantic attributes used fall into five groups: scene (e.g. `road...
The purpose of this paper is to build a digital archive database for Taiwanese people to learn Taiwanese culture through the internet and elearning environment. This study will be ...
Many current object class models build on visual parts that constitute an object. However, visually different entities may actually refer to the same object part. This may be harm...