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 proceedingConference contribution

581 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 languageEnglish (US)
Title of host publicationProceedings of the IEEE Conference on Computer Vision and Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages961-970
Number of pages10
ISBN (Print)9781467369640
DOIs
StatePublished - Oct 15 2015

Fingerprint Dive into the research topics of 'ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding'. Together they form a unique fingerprint.

Cite this