Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Distributed Hash Tables (DHTs) promise to manage huge sets of key-value pairs in a Peer-to-Peer manner. The Content-Addressable Network (CAN) is a prominent variant of DHT. A crit...
Handling large amounts of data, such as large image databases, requires the use of approximate nearest neighbor search techniques. Recently, Hamming embedding methods such as spec...
—A novel non-linear dimensionality reduction method, called Temporal Laplacian Eigenmaps, is introduced to process efficiently time series data. In this embedded-based approach,...
Michal Lewandowski, Jesus Martinez-Del-Rincon, Dim...
Recent improvements in positioning technology make massive moving object data widely available. One important analysis is to find the moving objects that travel together. Existin...