: Nowadays, advanced E-Learning systems are generally pedagogy-aware. Commonly, these systems include facilities for defining so-called learning scenarios that reflect sophisticate...
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
The aim of this paper is to address recognition of natural human actions in diverse and realistic video settings. This challenging but important subject has mostly been ignored in...
Ivan Laptev, Marcin Marszalek, Cordelia Schmid, Be...
While great strides have been made in detecting and localizing specific objects in natural images, the bottom-up segmentation of unknown, generic objects remains a difficult chall...
Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...