The DAVIS Challenge on Video Object Segmentation @ CVPR 2018

Organized by jponttuset - Current server time: May 19, 2019, 7:04 a.m. UTC

First phase

Test-Challenge 2017
June 18, 2017, 11:59 p.m. UTC

End

Competition Ends
April 5, 2019, 9 a.m. UTC

Welcome to the DAVIS Challenges!

This was the submission site for the DAVIS Challenges 2017 and 2018 on Video Object Segmentation. You can find more details about the challenge, dataset, prizes and rules in the DAVIS website.

Important!  We have moved to another competition page, therefore it is no longer possible to submit results in this site. In the new site, we have improved the evalutation scripts and the results should be computed 5 times faster! Please, register in the new competition here.  

Please cite the following papers if you participate in the challenge:

@article{Caelles_arXiv_2018,
  author = {Sergi Caelles and Alberto Montes and Kevis-Kokitsi Maninis and Yuhua Chen and Luc {Van Gool} and Federico Perazzi and Jordi Pont-Tuset},
  title = {The 2018 DAVIS Challenge on Video Object Segmentation},
  journal = {arXiv:1803.00557},
  year = {2018}
@article{Pont-Tuset_arXiv_2017,
  author = {Jordi Pont-Tuset and Federico Perazzi and Sergi Caelles and Pablo Arbel\'aez and Alexander Sorkine-Hornung and Luc {Van Gool}},
  title = {The 2017 DAVIS Challenge on Video Object Segmentation},
  journal = {arXiv:1704.00675},
  year = {2017}
} 
@inproceedings{Perazzi2016,
author = {F. Perazzi and J. Pont-Tuset and B. McWilliams and L. {Van Gool} and M. Gross and A. Sorkine-Hornung},
title = {A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation},
booktitle = {Computer Vision and Pattern Recognition},
year = {2016}
}

Evaluation Criteria

The evaluation of the results will be the mean over all objects and between the Region (IoU) and Boundary measures presented in the original CVPR 2016 DAVIS paper. The segmentation of the first frame is given. More details in the arXiv paper that can be found in the DAVIS website, and in the web itself.

Terms and Conditions

Please check the DAVIS website for details about terms and conditions.

Please cite the following papers if you participate in the challenge:

@article{Caelles_arXiv_2018,
  author = {Sergi Caelles and Alberto Montes and Kevis-Kokitsi Maninis and Yuhua Chen and Luc {Van Gool} and Federico Perazzi and Jordi Pont-Tuset},
  title = {The 2018 DAVIS Challenge on Video Object Segmentation},
  journal = {arXiv:1803.00557},
  year = {2018}
@article{Pont-Tuset_arXiv_2017,
  author = {Jordi Pont-Tuset and Federico Perazzi and Sergi Caelles and Pablo Arbel\'aez and Alexander Sorkine-Hornung and Luc {Van Gool}},
  title = {The 2017 DAVIS Challenge on Video Object Segmentation},
  journal = {arXiv:1704.00675},
  year = {2017}
}

 

@inproceedings{Perazzi2016,
author = {F. Perazzi and J. Pont-Tuset and B. McWilliams and L. {Van Gool} and M. Gross and A. Sorkine-Hornung},
title = {A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation},
booktitle = {Computer Vision and Pattern Recognition},
year = {2016}
}

Test-Challenge 2017

Start: June 18, 2017, 11:59 p.m.

Test-Dev

Start: June 30, 2017, 11:59 p.m.

Test-Challenge 2018

Start: May 13, 2018, 11:59 p.m.

Description: Find the leaderboard in https://davischallenge.org/challenge2018/semisupervised.html

Competition Ends

April 5, 2019, 9 a.m.

You must be logged in to participate in competitions.

Sign In