Relation Segmentation

Photo of author
Written By Zach Johnson

AI and tech enthusiast with a background in machine learning.


The PIC relation segmentation task is designed to push the process of visual understanding on middle level. Different from former works which focus on relation detection, the PIC relation segmentation takes one step forward that predict the relation between instance segmentations. Thanks to the fine-grained segmentation annotations, the relation prediction can be more precise. The PIC is a human-centric dataset which means the subject of relation triplet should always be human. And this characteristic makes the task closer to reality application such as intelligent babysitting and risk prediction.

This task is part of the 2nd Person in Context (PIC) Workshop and Challenge at ICCV 2019. For further details about the workshop please visit the workshop page. The winners will be invited to present at the workshop.

The evaluation server will still open to researchers after this challenge. But the results will not be presented at the challenge leaderboard. Instead a dev-leaderboard will be promoted to show all the results. And we encourage the community to keep focusing on this topic.

 Important Date

Time zone: Beijing, UTC+8

Aug. 22th, 00:05:00, 2019

Aug. 31th, 00:05:00, 2019

Oct. 18th, 00:05:00, 2019

Oct. 20th, 00:05:00, 2019

Oct. 28th, 2019

Training / validation set released

Testing set released and submission opened

Submission deadline

Challenge winners notified

Winners present at ICCV 2019 Workshop

 Task Rules

  1. Make sure the submission format has met the requirements. See
  2. Using extra training data are not allowded. But the usage of pretrain model has no limitations.
  3. You have 10 submission chances in total.
  4. The evaluation process can takes times. And a failed submission will not cause the reduction of submission chances.

AI is evolving. Don't get left behind.

AI insights delivered straight to your inbox.

Please enable JavaScript in your browser to complete this form.