This work addresses the problem of human action recognition by introducing a representation of a human action as a collection of short trajectories that are extracted in areas of ...
Antonios Oikonomopoulos, Ioannis Patras, Maja Pant...
: A new method is presented to learn object categories from unlabeled and unsegmented images for generic object recognition. We assume that each object can be characterized by a se...
Andreas Opelt, Axel Pinz, Michael Fussenegger, Pet...
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...
We introduce an algorithm for a non-negative 3D tensor factorization for the purpose of establishing a local parts feature decomposition from an object class of images. In the pas...
Abstract. We propose a novel Multiple Instance Learning (MIL) framework to perform target localization from image sequences. The proposed approach consists of a softmax logistic re...