Weakly Supervised Action Localization by Sparse Temporal Pooling Network

@article{Nguyen2017WeaklySA,
  title={Weakly Supervised Action Localization by Sparse Temporal Pooling Network},
  author={Phuc Nguyen and Ting Liu and Gautam Prasad and Bohyung Han},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2017},
  pages={6752-6761}
}
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

Citations

Publications citing this paper.
SHOWING 1-10 OF 26 CITATIONS

GRAPH REGULARIZATION NETWORK WITH SEMANTIC AFFINITY FOR WEAKLY-SUPERVISED TEMPORAL ACTION LOCALIZATION

Jungin Park, Ji Young Lee, Sangryul Jeon, Seungryong Kim, Kwanghoon Sohn
  • 2019
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Weakly Supervised Gaussian Networks for Action Detection

VIEW 7 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 52 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 INFLUENTIAL

UntrimmedNets for Weakly Supervised Action Recognition and Detection

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

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

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Learning Deep Features for Discriminative Localization

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

The Kinetics Human Action Video Dataset

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

THUMOS challenge: Action recognition with a large number of classes

Y.-G. Jiang, J. Liu, +4 authors R. Sukthankar
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 1 EXCERPT

Similar Papers