Learning spatiotemporal features with 3D convolutional networks

Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.

Original languageEnglish (US)
Title of host publication2015 International Conference on Computer Vision, ICCV 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4489-4497
Number of pages9
ISBN (Electronic)9781467383912
DOIs
StatePublished - Feb 17 2015
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: Dec 11 2015Dec 18 2015

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)1550-5499

Other

Other15th IEEE International Conference on Computer Vision, ICCV 2015
CountryChile
CitySantiago
Period12/11/1512/18/15

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Learning spatiotemporal features with 3D convolutional networks'. Together they form a unique fingerprint.

Cite this