Actom Sequence Models for Efficient Action Detection

Adrien Gaidon 1, 2 Zaid Harchaoui 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We address the problem of detecting actions, such as drinking or opening a door, in hours of challenging video data. We propose a model based on a sequence of atomic action units, termed ''actoms'', that are characteristic for the action. Our model represents the temporal structure of actions as a sequence of histograms of actom-anchored visual features. Our representation, which can be seen as a temporally structured extension of the bag-of-features, is flexible, sparse and discriminative. We refer to our model as Actom Sequence Model (ASM). Training requires the annotation of actoms for action clips. At test time, actoms are detected automatically, based on a non-parametric model of the distribution of actoms, which also acts as a prior on an action's temporal structure. We present experimental results on two recent benchmarks for temporal action detection. We show that our ASM method outperforms the current state of the art in temporal action detection.
Document type :
Conference papers
CVPR 2011 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.3201-3208, 2011, <10.1109/CVPR.2011.5995646>
Liste complète des métadonnées



https://hal.inria.fr/inria-00575217
Contributor : Thoth Team <>
Submitted on : Wednesday, April 6, 2011 - 3:44:53 PM
Last modification on : Monday, July 14, 2014 - 10:47:33 PM
Document(s) archivé(s) le : Thursday, July 7, 2011 - 2:29:57 AM

Identifiers

Collections

Citation

Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid. Actom Sequence Models for Efficient Action Detection. CVPR 2011 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.3201-3208, 2011, <10.1109/CVPR.2011.5995646>. <inria-00575217>

Share

Metrics

Record views

2314

Document downloads

3629