ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding

Fabian Caba Heilbron; Victor Castillo; Bernard Ghanem; Juan Carlos Niebles

doi:10.1109/CVPR.2015.7298698

ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding

Fabian Caba Heilbron, Victor Castillo, Bernard Ghanem, Juan Carlos Niebles

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

1318 Scopus citations

Abstract

In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new largescale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: untrimmed video classification, trimmed activity classification and activity detection.

Original language	English (US)
Title of host publication	Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	961-970
Number of pages	10
ISBN (Print)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7298698
State	Published - Oct 15 2015

Bibliographical note

KAUST Repository Item: Exported on 2020-04-23
Acknowledgements: IEEE Computer Society, Computer Vision Foundation - CVF

Access to Document

10.1109/CVPR.2015.7298698

https://repository.kaust.edu.sa/bitstream/10754/556141/1/ActivityNet_CVPR2015.pdf

Cite this

@inproceedings{409a86fdbca64391bea0686499b52354,

title = "ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding",

abstract = "In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new largescale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: untrimmed video classification, trimmed activity classification and activity detection.",

author = "Heilbron, {Fabian Caba} and Victor Castillo and Bernard Ghanem and Niebles, {Juan Carlos}",

note = "KAUST Repository Item: Exported on 2020-04-23 Acknowledgements: IEEE Computer Society, Computer Vision Foundation - CVF",

year = "2015",

month = oct,

day = "15",

doi = "10.1109/CVPR.2015.7298698",

language = "English (US)",

isbn = "9781467369640",

pages = "961--970",

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

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding. / Heilbron, Fabian Caba; Castillo, Victor; Ghanem, Bernard et al.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 961-970.

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

TY - GEN

T1 - ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding

AU - Heilbron, Fabian Caba

AU - Castillo, Victor

AU - Ghanem, Bernard

AU - Niebles, Juan Carlos

N1 - KAUST Repository Item: Exported on 2020-04-23 Acknowledgements: IEEE Computer Society, Computer Vision Foundation - CVF

PY - 2015/10/15

Y1 - 2015/10/15

N2 - In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new largescale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: untrimmed video classification, trimmed activity classification and activity detection.

AB - In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new largescale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes with an average of 137 untrimmed videos per class and 1.41 activity instances per video, for a total of 849 video hours. We illustrate three scenarios in which ActivityNet can be used to compare algorithms for human activity understanding: untrimmed video classification, trimmed activity classification and activity detection.

UR - http://hdl.handle.net/10754/556141

UR - https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Heilbron_ActivityNet_A_Large-Scale_2015_CVPR_paper.pdf

UR - http://www.scopus.com/inward/record.url?scp=84959216468&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298698

DO - 10.1109/CVPR.2015.7298698

M3 - Conference contribution

AN - SCOPUS:84959216468

SN - 9781467369640

SP - 961

EP - 970

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

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this