• DOI:10.1109/ICCV.2017.235
Corpus ID: 2930562

What Actions are Needed for Understanding Human Actions in Videos?

@article{Sigurdsson2017WhatAA,
  title={What Actions are Needed for Understanding Human Actions in Videos?},
  author={Gunnar A. Sigurdsson and Olga Russakovsky and A. Gupta},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={2156-2165}
}

Gunnar A. Sigurdsson, Olga Russakovsky, A. Gupta

Published 2017

Computer Science

2017 IEEE International Conference on Computer Vision (ICCV)

What is the right way to reason about human activities? What directions forward are most promising? In this work, we analyze the current state of human activity understanding in videos. The goal of this paper is to examine datasets, evaluation metrics, algorithms, and potential future directions. We look at the qualitative attributes that define activities such as pose variability, brevity, and density. The experiments consider multiple state-of-the-art algorithms and multiple datasets. The… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed