TY - GEN
T1 - ActivityNet
T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
AU - Heilbron, Fabian Caba
AU - Escorcia, Victor
AU - Ghanem, Bernard
AU - Niebles, Juan Carlos
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/10/14
Y1 - 2015/10/14
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 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.
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 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.
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
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 961
EP - 970
BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PB - IEEE Computer Society
Y2 - 7 June 2015 through 12 June 2015
ER -