Actions and Attributes from Wholes and Parts

@article{Gkioxari2014ActionsAA,
  title={Actions and Attributes from Wholes and Parts},
  author={Georgia Gkioxari and Ross B. Girshick and Jitendra Malik},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2014},
  pages={2470-2478}
}
We investigate the importance of parts for the tasks of action and attribute classification. We develop a part-based approach by leveraging convolutional network features inspired by recent advances in computer vision. Our part detectors are a deep version of poselets and capture parts of the human body under a distinct set of poses. For the tasks of action and attribute classification, we train holistic convolutional neural networks and show that adding parts leads to top-performing results… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 62 CITATIONS

Action Recognition in Still Images With Minimum Annotation Efforts

  • IEEE Transactions on Image Processing
  • 2016
VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Survey to Deep Facial Attribute Analysis

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Attribute And-Or Grammar for Joint Parsing of Human Pose, Parts and Attributes

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
VIEW 10 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose

VIEW 10 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Single Image Action Recognition Using Semantic Body Part Actions

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2016
VIEW 7 EXCERPTS
HIGHLY INFLUENCED

Contextual Action Recognition with R*CNN

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS

Image context for object detection, object context for part detection

VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reassessing Hierarchical Representation for Action Recognition in Still Images

  • IEEE Access
  • 2018
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Action Recognition from Still Images Based on Deep VLAD Spatial Pyramids

  • Sig. Proc.: Image Comm.
  • 2017
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 13 Highly Influenced Citations

  • Averaged 12 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 26 REFERENCES

PANDA: Pose Aligned Networks for Deep Attribute Modeling

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Deformable part models are convolutional neural networks

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014
VIEW 2 EXCERPTS