Asynchronous Temporal Fields for Action Recognition

@article{Sigurdsson2016AsynchronousTF,
  title={Asynchronous Temporal Fields for Action Recognition},
  author={Gunnar A. Sigurdsson and Santosh Kumar Divvala and Ali Farhadi and Abhinav Gupta},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={5650-5659}
}
Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of activities, as well as the higher-level constructs such as intentions. But how do we model and reason about these? We propose a fully-connected temporal CRF model for reasoning over various aspects of activities that includes objects, actions, and intentions, where… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 71 CITATIONS

Weakly Supervised Gaussian Networks for Action Detection

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Statistical Machine Learning vs Deep Learning in Information Fusion: Competition or Collaboration?

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

What Actions are Needed for Understanding Human Actions in Videos?

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS

Discriminative Video Representation Learning Using Support Vector Classifiers

  • Jue Wang, Anoop Cherian
  • Computer Science, Medicine
  • IEEE transactions on pattern analysis and machine intelligence
  • 2019
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph

VIEW 16 EXCERPTS
CITES BACKGROUND & METHODS

Recurrent Neural Networks

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

R-C3D: Region Convolutional 3D Network for Temporal Activity Detection

VIEW 4 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Focused Attention for Action Recognition

VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Learning Differentiable Grammars for Continuous Data

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 12 Highly Influenced Citations

  • Averaged 23 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 67 REFERENCES

Action Recognition with Improved Trajectories

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Actions ~ Transformations

VIEW 2 EXCERPTS

Situation Recognition: Visual Semantic Role Labeling for Image Understanding

VIEW 2 EXCERPTS

Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs

VIEW 1 EXCERPT