Automatic Discovery of Action Taxonomies from Multiple Views

Daniel Weinland 1 Rémi Ronfard 1, * Edmond Boyer 1
* Corresponding author
1 PERCEPTION - Interpretation and Modelling of Images and Videos
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner using examples recorded by multiple cameras. Segmentation and clustering of action classes is based on a recently proposed motion descriptor which can be extracted ef ciently from reconstructed volume sequences. Because our representation is independent of viewpoint, it results in segmentation and classi cation methods which are surprisingly ef cient and robust. Our new method can be used as the rst step in a semi-supervised action recognition system that will automatically break down training examples of people performing sequences of actions into primitive actions that can be discriminatingly classi ed and assembled into high-level recognizers.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download


https://hal.inria.fr/inria-00590216
Contributor : Team Perception <>
Submitted on : Tuesday, May 3, 2011 - 9:39:24 AM
Last modification on : Wednesday, April 11, 2018 - 1:54:48 AM
Long-term archiving on : Thursday, August 4, 2011 - 3:06:13 AM

Identifiers

Collections

INRIA | UGA | IMAG

Citation

Daniel Weinland, Rémi Ronfard, Edmond Boyer. Automatic Discovery of Action Taxonomies from Multiple Views. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '06), Jun 2006, New York, United States. pp.1639--1645, ⟨10.1109/CVPR.2006.65⟩. ⟨inria-00590216⟩

Share

Metrics

Record views

612

Files downloads

370