Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geo...
Anh Phuong Ta, Christian Wolf, Guillaume Lavoue, A...
The popular bag-of-words paradigm for action recognition tasks is based on building histograms of quantized features, typically at the cost of discarding all information about rela...
Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the rel...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
We present a novel human action recognition system based on segmented skeletal features which are separated into several human body parts such as face, torso and limbs. Our propos...