We introduce a new perceptron-based discriminative learning algorithm for labeling structured data such as sequences, trees, and graphs. Since it is fully kernelized and uses poin...
We study the problem of event detection from realistic videos with repetitive sequential human activities. Despite the large body of work on event detection and recognition, very ...
Lei Ding, Quanfu Fan, Jen-Hao Hsiao, Sharath Panka...
`Approximate message passing' algorithms proved to be extremely effective in reconstructing sparse signals from a small number of incoherent linear measurements. Extensive num...
Let K− r denote the graph obtained from Kr by deleting one edge. We show that for every integer r ≥ 4 there exists an integer n0 = n0(r) such that every graph G whose order n â...
A large hypertext net with node-to-node links can be interesting as a system of unities of meaning formed by node clusters, such that nodes in each of them are orderable into a co...