Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images

@article{Mottaghi2015NewtonianIU,
  title={Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images},
  author={Roozbeh Mottaghi and Hessam Bagherinezhad and Mohammad Rastegari and Ali Farhadi},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={3521-3529}
}
In this paper, we study the challenging problem of predicting the dynamics of objects in static images. Given a query object in an image, our goal is to provide a physical understanding of the object in terms of the forces acting upon it and its long term motion as response to those forces. Direct and explicit estimation of the forces and the motion of objects from a single image is extremely challenging. We define intermediate physical abstractions called Newtonian scenarios and introduce… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 84 CITATIONS, ESTIMATED 98% COVERAGE

LEARNING PHYSICAL DYNAMICS

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Adaptive Visual Interaction Based Multi-Target Future State Prediction For Autonomous Driving Vehicles

VIEW 1 EXCERPT
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2015
2020

CITATION STATISTICS

  • 3 Highly Influenced Citations

  • Averaged 22 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Dense Optical Flow Prediction from a Static Image

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Detecting potential falling objects by inferring human action and natural disturbance

VIEW 1 EXCERPT

Learning Spatiotemporal Features with 3D Convolutional Networks

VIEW 2 EXCERPTS

Patch to the Future: Unsupervised Visual Prediction

VIEW 1 EXCERPT

Predicting Object Dynamics in Scenes

VIEW 1 EXCERPT