Discriminative Hierarchical Rank Pooling for Activity Recognition

Basura Fernando; Peter Anderson; Marcus Hutter; Stephen Gould

doi:10.1109/CVPR.2016.212

Discriminative Hierarchical Rank Pooling for Activity Recognition

Basura Fernando, Peter Anderson, Marcus Hutter, Stephen Gould

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

89 Citations (Scopus)

Abstract

We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which is used for action recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Publisher	IEEE Computer Society
Pages	1924-1932
Number of pages	9
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.212
Publication status	Published - 9 Dec 2016
Event	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States Duration: 26 Jun 2016 → 1 Jul 2016

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2016-December
ISSN (Print)	1063-6919

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Country/Territory	United States
City	Las Vegas
Period	26/06/16 → 1/07/16

Access to Document

10.1109/CVPR.2016.212

Cite this

Fernando, B., Anderson, P., Hutter, M., & Gould, S. (2016). Discriminative Hierarchical Rank Pooling for Activity Recognition. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 1924-1932). Article 7780581 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.212

@inproceedings{dd9c780adf334207a386dce984010b0e,

title = "Discriminative Hierarchical Rank Pooling for Activity Recognition",

abstract = "We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which is used for action recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.",

author = "Basura Fernando and Peter Anderson and Marcus Hutter and Stephen Gould",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

year = "2016",

month = dec,

day = "9",

doi = "10.1109/CVPR.2016.212",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "1924--1932",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",

address = "United States",

}

Fernando, B, Anderson, P, Hutter, M & Gould, S 2016, Discriminative Hierarchical Rank Pooling for Activity Recognition. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780581, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 1924-1932, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 26/06/16. https://doi.org/10.1109/CVPR.2016.212

Discriminative Hierarchical Rank Pooling for Activity Recognition. / Fernando, Basura; Anderson, Peter; Hutter, Marcus et al.
Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 1924-1932 7780581 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Discriminative Hierarchical Rank Pooling for Activity Recognition

AU - Fernando, Basura

AU - Anderson, Peter

AU - Hutter, Marcus

AU - Gould, Stephen

PY - 2016/12/9

Y1 - 2016/12/9

N2 - We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which is used for action recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.

AB - We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which is used for action recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.

UR - http://www.scopus.com/inward/record.url?scp=84986290213&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.212

DO - 10.1109/CVPR.2016.212

M3 - Conference contribution

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1924

EP - 1932

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Fernando B, Anderson P, Hutter M, Gould S. Discriminative Hierarchical Rank Pooling for Activity Recognition. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 1924-1932. 7780581. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2016.212

Discriminative Hierarchical Rank Pooling for Activity Recognition

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this