In this paper, we study the problem of semi-supervised image recognition, which is to learn
classifiers using both labeled and unlabeled images. We present Deep Co-Training, a deep …

Despite the advances in machine learning techniques, similarity assessment among
multimedia data remains a challenging task of broad interest in computer science …

Learning an ideal metric is crucial to many tasks in computer vision. Diverse feature
representations may combat this problem from different aspects; as visual data objects …

In this paper, we propose a novel label propagation-based method for saliency detection. A
key observation is that saliency in an image can be estimated by propagating the labels …

摘要传统监督学习通常需使用大量有标记的数据样本作为训练例, 而在很多现实问题中,
人们虽能容易地获得大批数据样本, 但为数据提供标记却需耗费很多人力物力. 那么 …

In this paper, we propose an extremely efficient algorithm for visual re-ranking. By
considering the original pairwise distance in the contextual space, we develop a feature …

We propose a novel shape descriptor for matching and recognizing 2D object silhouettes.
The contour of each object is represented by a fixed number of sample points. For each …

In graph-based semi-supervised learning approaches, the classification rate is highly
dependent on the size of the availabel labeled data, as well as the accuracy of the similarity …

摘要形状匹配及分类是计算机视觉中的重要问题. 近年来, 以形状上下文为代表的基于轮廓的
形状匹配方法和以奇点图为代表的基于骨架的形状匹配方法获得了长足的发展 …

In many applications, we are given a finite set of data points sampled from a data manifold
and represented as a graph with edge weights determined by pairwise similarities of the …