ActivityNet: A large-scale video benchmark for human activity understanding

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 ac...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 961 - 970
Hlavní autoři: Caba Heilbron, Fabian, Escorcia, Victor, Ghanem, Bernard, Niebles, Juan Carlos
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.06.2015
Témata:
Algorithms
Benchmark testing
Benchmarking
Classification
Cleaning
Complexity theory
Computer vision
Conferences
Human motion
Movements
Organizations
Pattern recognition
Semantics
Taxonomy
YouTube
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 large-scale 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.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2015.7298698