Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis.

Christian Theriault Nicolas Thome 1 Matthieu Cord 1
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : In this paper, we address the challenging problem of categorizing video sequences composed of dynamic natural scenes. Contrarily to previous methods that rely on handcrafted descriptors, we propose here to represent videos using unsupervised learning of motion features. Our method encompasses three main contributions: 1) Based on the Slow Feature Analysis principle, we introduce a learned local motion descriptor which represents the principal and more stable motion components of training videos. 2) We integrate our local motion feature into a global coding/pooling architecture in order to provide an effective signature for each video sequence. 3) We report state of the art classification performances on two challenging natural scenes data sets. In particular, an outstanding improvement of 11% in classification score is reached on a data set introduced in 2012.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01216646
Contributor : Lip6 Publications <>
Submitted on : Friday, October 16, 2015 - 3:37:43 PM
Last modification on : Thursday, March 21, 2019 - 2:31:14 PM

Links full text

Identifiers

Citation

Christian Theriault, Nicolas Thome, Matthieu Cord. Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis.. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, OR, United States. IEEE, pp.2603-2610, 〈10.1109/CVPR.2013.336〉. 〈hal-01216646〉

Share

Metrics

Record views

98