Nonnegative matrix tri-factorization (NMTF) is a 3-factor decomposition of a nonnegative data matrix, X USV , where factor matrices, U, S, and V , are restricted to be nonnegativ...
This paper examines the problem of moving object detection. More precisely, it addresses the difficult scenarios where background scene textures in the video might change over tim...
Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new r...
Abstract—Segmentation of architectural floorplans is a challenging task, mainly because of the large variability in the notation between different plans. In general, traditional...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...