inria-00459653, version 1
A Survey of Vision-Based Methods for Action Representation, Segmentation and Recognition
Daniel Weinland
a, 1Rémi Ronfard
b, 2Edmond Boyer
c, 3, 4
N° RR-7212 (2010)
Abstract: Action recognition has become a very important topic in computer vision, with many fundamental applications, in robotics, video surveillance, human computer interaction and multimedia retrieval among others. The number of works published is steadily increasing and action recognition is meanwhile presented with numerous publications at recent conferences. A large variety of approaches have been described. The purpose of this survey is to give an overview and categorization of the approaches used.
- a – Deutsche Telekom Laboratories
- b – INRIA
- c – Université Joseph Fourier - Grenoble I
- 1: Deutsche Telekom Laboratories (DT Lab)
- Deutsche Telekom Laboratories
- 2: LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- 3: PERCEPTION (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- INRIA – Laboratoire Jean Kuntzmann – CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG) – Université Pierre Mendès-France - Grenoble II
- 4: MORPHEO (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
- INRIA – Institut National Polytechnique de Grenoble (INPG) – Université Joseph Fourier - Grenoble I
- Domain : Computer Science/Computer Vision and Pattern Recognition
- Internal note : RR-7212
- inria-00459653, version 1
- http://hal.inria.fr/inria-00459653
- oai:hal.inria.fr:inria-00459653
- From: Edmond Boyer
- Submitted on: Wednesday, 24 February 2010 16:02:49
- Updated on: Monday, 30 May 2011 18:08:52






Associated documents
Export