A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which...
We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner ...
In this paper, we propose a generative model-based approach for audio-visual event classification. This approach is based on a new unsupervised learning method using an extended p...
Ming Li, Sanqing Hu, Shih-Hsi Liu, Sung Baang, Yu ...
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Many unsupervised algorithms for nonlinear dimensionality reduction, such as locally linear embedding (LLE) and Laplacian eigenmaps, are derived from the spectral decompositions o...