Common Action Discovery and Localization in Unconstrained Videos

@article{Yang2017CommonAD,
  title={Common Action Discovery and Localization in Unconstrained Videos},
  author={Jiong Yang and Junsong Yuan},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={2176-2185}
}
Similar to common object discovery in images or videos, it is of great interests to discover and locate common actions in videos, which can benefit many video analytics applications such as video summarization, search, and understanding. In this work, we tackle the problem of common action discovery and localization in unconstrained videos, where we do not assume to know the types, numbers or locations of the common actions in the videos. Furthermore, each video can contain zero, one or several… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • The proposed method successfully selects the proposals containing common actions, and improves the average precision by more than 20% percent in all the datasets and IOU settings.

References

Publications referenced by this paper.
SHOWING 1-10 OF 48 REFERENCES

Discovering Thematic Patterns in Videos via Cohesive Sub-graph Mining

  • 2011 IEEE 11th International Conference on Data Mining
  • 2011
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Finding a Maximum Density Subgraph

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Towards Understanding Action Recognition

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Discovering the Physical Parts of an Articulated Object Class from Multiple Videos

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 2 EXCERPTS