We propose and investigate a paradigm for activity recognition, distinguishing the ‘on-going activity’ recognition task (OGA) from that addressing ‘complete activities’ (C...
Bruno Lepri, Nadia Mana, Alessandro Cappelletti, F...
Abstract. The recognition of events in videos is a relevant and challenging task of automatic semantic video analysis. At present one of the most successful frameworks, used for ob...
Lamberto Ballan, Marco Bertini, Alberto Del Bimbo,...
Human behavior recognition is one of the most important and challenging objectives performed by intelligent vision systems. Several issues must be faced in this domain ranging fro...
Abstract-The CALO Meeting Assistant (MA) provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of ...
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...