In this paper, we propose a multimodal system for detecting human activity and interaction patterns in a nursing home. Activities of groups of people are firstly treated as intera...
The increasing power of techniques to model complex geometry and extract meaning from 3D information create complex data that must be described, stored, and displayed to be useful...
Several novel and particularly successful object and object category detection and recognition methods based on image features, local descriptions of object appearance, have recent...
Jarmo Ilonen, Joni-Kristian Kamarainen, Pekka Paal...
Sparse coding is a key principle that underlies wavelet representation of natural images. In this paper, we explain that the effort of seeking a common wavelet sparse coding of i...
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...