Weakly Supervised Action Localization by Sparse Temporal Pooling Network

@inproceedings{Nguyen2018WeaklySA,
  title={Weakly Supervised Action Localization by Sparse Temporal Pooling Network},
  author={Phuc Nguyen and Ting Liu and Gautam Prasad and Bohyung Han},
  booktitle={CVPR},
  year={2018}
}
We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no requirement of temporal localization annotations. We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling. Our loss function… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 22 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 51 references

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 10 Excerpts
Highly Influenced

UntrimmedNets for Weakly Supervised Action Recognition and Detection

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 6 Excerpts
Highly Influenced

Learning Deep Features for Discriminative Localization

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 4 Excerpts
Highly Influenced

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

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 13 Excerpts
Highly Influenced

The Kinetics Human Action Video Dataset

ArXiv • 2017
View 5 Excerpts
Highly Influenced

THUMOS challenge: Action recognition with a large number of classes

Y.-G. Jiang, J. Liu, +4 authors R. Sukthankar
2014
View 4 Excerpts
Highly Influenced

ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 1 Excerpt

Similar Papers

Loading similar papers…