Skip to Main content Skip to Navigation
New interface
Conference papers

An Unsupervised Framework for Action Recognition Using Actemes

Kaustubh Kulkarni 1 Edmond Boyer 1 Radu Horaud 1 Amit Kale 2 
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : In speech recognition, phonemes have demonstrated their ef- ficacy to model the words of a language. While they are well defined for languages, their extension to human actions is not straightforward. In this paper, we study such an extension and propose an unsupervised framework to find phoneme-like units for actions, which we call actemes, using 3D data and without any prior assumptions. To this purpose, build on an earlier proposed framework in speech literature to automatically find actemes in the training data. We experimentally show that actions defined in terms of actemes and actions defined by whole units give simi- lar recognition results. We define actions out of the training set in terms of these actemes to see whether the actemes generalize to unseen actions. The results show that although the acteme definitions of the actions are not always semantically meaningful, they yield optimal recognition accu- racy and constitute a promising direction of research for action modeling.
Document type :
Conference papers
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download
Contributor : Edmond Boyer Connect in order to contact the contributor
Submitted on : Wednesday, February 23, 2011 - 7:23:31 PM
Last modification on : Saturday, November 5, 2022 - 3:51:22 AM
Long-term archiving on: : Tuesday, May 24, 2011 - 4:31:15 AM


Files produced by the author(s)



Kaustubh Kulkarni, Edmond Boyer, Radu Horaud, Amit Kale. An Unsupervised Framework for Action Recognition Using Actemes. ACCV 2010 - 10th Asian Conference on Computer Vision, Nov 2010, Queenstown, New Zealand. pp.592-605, ⟨10.1007/978-3-642-19282-1_47⟩. ⟨inria-00568906⟩



Record views


Files downloads