A chains model for localizing participants of group activities in videos

@article{Amer2011ACM,
  title={A chains model for localizing participants of group activities in videos},
  author={Mohammed Abdel Rahman Amer and Sinisa Todorovic},
  journal={2011 International Conference on Computer Vision},
  year={2011},
  pages={786-793}
}
Given a video, we would like to recognize group activities, localize video parts where these activities occur, and detect actors involved in them. This advances prior work that typically focuses only on video classification. We make a number of contributions. First, we specify a new, mid-level, video feature aimed at summarizing local visual cues into bags of the right detections (BORDs). BORDs seek to identify the right people who participate in a target group activity among many noisy people… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 50 CITATIONS

Recognizing Interactive Group Activities Using Temporal Interaction Matrices and Their Riemannian Statistics

  • International Journal of Computer Vision
  • 2012
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Collective Activity Recognition Using Naïve Bayes Classifiers

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Finding Group Interactions in Social Clutter

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 8 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Understanding Complex Human Behaviour in Images and Videos

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A survey of group activity recognition in smart building

  • 2018 International Conference on Signals and Systems (ICSigSys)
  • 2018
VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2018

CITATION STATISTICS

  • 15 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities

  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

What are they doing? : Collective activity classification using spatio-temporal relationship among people

  • 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops
  • 2009
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Discriminatively trained deformable part models

P. Felzenszwalb, R. Girshick, D. McAllester
  • CVPR,
  • 2008
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Object matching with a locally affine-invariant constraint

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 1 EXCERPT

Secrets of optical flow estimation and their principles

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 2 EXCERPTS

The chains model for detecting parts by their context

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 1 EXCERPT