Automatic Discovery of Action Taxonomies from Multiple Views - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Automatic Discovery of Action Taxonomies from Multiple Views


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.
Fichier principal
Vignette du fichier
1137_weinland_d.pdf (886.17 Ko) Télécharger le fichier
Vignette du fichier
discovery.png (147.05 Ko) Télécharger le fichier
DoAT_low.avi (13.12 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Other

Dates and versions

inria-00590216 , version 1 (03-05-2011)



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⟩
295 View
244 Download



Gmail Facebook X LinkedIn More