In partial-duplicate image retrieval, images are commonly represented using Bag-of-visual-Words (BoW) built from image local features, such as SIFT. Therefore, the discriminative ...
The key to real-time rendering of large-scale surfaces is to locally adapt surface geometric complexity to changing view parameters. Several schemes have been developed to address...
Semi-supervised image segmentation is an important issue in many image processing applications, and has been a popular research area recently, the most popular are graph-based met...
Probabilistic feature relevance learning (PFRL) is an effective method for adaptively computing local feature relevance in content-based image retrieval. It computes flexible retr...
One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performa...