Action-vectors: Unsupervised movement modeling for action recognition

Conference/Journal
IEEE
Authors
Debaditya Roy K Sri Rama Murty C. Krishna Mohan
BibTex
Abstract
Abstract: Representation and modelling of movements play a significant role in recognising actions in unconstrained videos. However, explicit segmentation and labelling of movements are non-trivial because of the variability associated with actors, camera viewpoints, duration etc. Therefore, we propose to train a GMM with a large number of components termed as a universal movement model (UMM). This UMM is trained using motion boundary histograms (MBH) which capture the motion trajectories associated with ...