Learning Spatiotemporal Features with 3D Convolutional Networks

被引：6066

作者：

Du Tran ^{[1
,2
]}

Bourdev, Lubomir ^{[1
]}

Fergus, Rob ^{[1
]}

Torresani, Lorenzo ^{[2
]}

Paluri, Manohar ^{[1
]}

机构：

[1] Facebook AI Res, Menlo Pk, CA USA

[2] Dartmouth Coll, Hanover, NH 03755 USA

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2015年

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/ICCV.2015.510

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 3 x 3 x 3 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.

引用

页码：4489 / 4497

页数：9