Actions ~ Transformations

@article{Wang2016ActionsT,
  title={Actions ~ Transformations},
  author={Xiaolong Wang and Ali Farhadi and Abhinav Gupta},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2658-2667}
}
What defines an action like "kicking ball"? We argue that the true meaning of an action lies in the change or transformation an action brings to the environment. In this paper, we propose a novel representation for actions by modeling an action as a transformation which changes the state of the environment before the action happens (precondition) to the state after the action (effect). Motivated by recent advancements of video representation using deep learning, we design a Siamese network… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 117 CITATIONS

REPRESENTATION LEARNING FOR ACTION RECOGNITION

VIEW 10 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Deep Manifold Structure Transfer for Action Recognition

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Computer Vision – ECCV 2018

VIEW 9 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Switchable Temporal Propagation Network

VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Temporal Difference Networks for Video Action Recognition

VIEW 8 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Two-Stream 3-D convNet Fusion for Action Recognition in Videos With Arbitrary Size and Length

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

ConvNet Architecture Search for Spatiotemporal Feature Learning

VIEW 11 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Beyond Action Recognition: Action Completion in RGB-D Data

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Spatio-temporal Video Autoencoder for Human Action Recognition

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 15 Highly Influenced Citations

  • Averaged 33 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 63 REFERENCES

Towards Good Practices for Very Deep Two-Stream ConvNets

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Action Recognition with Improved Trajectories

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Large-Scale Video Classification with Convolutional Neural Networks

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Action Recognition by Hierarchical Mid-Level Action Elements

VIEW 1 EXCERPT

Action recognition with trajectory-pooled deep-convolutional descriptors

VIEW 3 EXCERPTS

ActivityNet: A large-scale video benchmark for human activity understanding

VIEW 2 EXCERPTS

Beyond short snippets: Deep networks for video classification

VIEW 3 EXCERPTS

DevNet: A Deep Event Network for multimedia event detection and evidence recounting

VIEW 1 EXCERPT

Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks

VIEW 1 EXCERPT