A Closer Look at Spatiotemporal Convolutions for Action Recognition

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 6450 - 6459
Main Authors Tran, Du, Wang, Heng, Torresani, Lorenzo, Ray, Jamie, LeCun, Yann, Paluri, Manohar
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Computer architecture
Feature extraction
Solid modeling
Spatiotemporal phenomena
Three-dimensional displays
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary:In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework of residual learning. Furthermore, we show that factorizing the 3D convolutional filters into separate spatial and temporal components yields significantly gains in accuracy. Our empirical study leads to the design of a new spatiotemporal convolutional block "R(2+1)D" which produces CNNs that achieve results comparable or superior to the state-of-the-art on Sports-1M, Kinetics, UCF101, and HMDB51.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00675