Procedural Human Action Videos

Deep learning for human action recognition in videos is making significant progress but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition

Released in: Procedural Human Action Videos

Source: arXiv - Procedural Generation of Videos to Train Deep Action Recognition Networks

Contributor:

by

Homepage

Summary

Deep learning for human action recognition in videos is making significant progress but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition

39,982

Images in dataset

07/2017

Year Released

Key Links & Stats

Custom - non-commercial scientific research purposes

@inproceedings{DeSouza:Procedural:CVPR2017, author = {De Souza, C R and Gaidon, A and Cabon, Y and Lopez Pena, A M }, title = {Procedural Generation of Videos to Train Deep Action Recognition Networks}, booktitle = {CVPR}, year = {2017} }

scenebox

Modalities

  1. Video

Verticals

  1. Satellite
  2. A/V

ML Task

  1. Human Pose Estimation
  2. Activity Recognition

Related organizations