Relation Segmentation


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 segmentaion takes one step forwad that predict the relation between instance segmentations. Thanks to the fine-grained segmentation annotaions, 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 evalation 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.

Task Metric