Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated ...
Many document collections are by nature dynamic, evolving as the topics or events they describe change. The goal of temporal text mining is to discover bursty patterns and to ident...
Dynamic appearance is one of the most important cues for tracking and identifying moving people. However, direct modeling spatio-temporal variations of such appearance is often a ...
Hwasup Lim, Octavia I. Camps, Mario Sznaier, Vlad ...
— There is a growing interest in developing low cost, low power, highly integrated biosensor systems to characterize individual cells for applications such as cell analysis, drug...
Honghao Ji, Pamela Abshire, M. Urdaneta, Elisabeth...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...