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...
We propose a human action clustering method based on a 3D representation of the body in terms of volumetric coordinates. Features representing body postures are extracted directly...
Massimiliano Pierobon, Marco Marcon, Augusto Sarti...
This paper presents a new behavior classification system for analyzing human movements directly from video sequences. First of all, we propose a triangulation-based method to tran...
We consider the fully automated recognition of actions in uncontrolled environment. Most existing work relies on domain knowledge to construct complex handcrafted features from in...
We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...