PIC 2018 Relation Segmentation Task

Introduction

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 1st Person in Context (PIC) Workshop and Challenge at ECCV 2018. 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: CET, UTC+2

July 1st 00:05:00, 2018
August 1st 00:05:00, 2018
August 4th 00:05:00, 2018
September 9th, 2018
Testing set released and submission opened
Submission deadline
Challenge winners notified
Winners present at ECCV 2018 Workshop

Task Awards

NVIDIA Titan V * 2

1st Place

NVIDIA Titan Xp * 2

2nd Place

NVIDIA 1080Ti * 2

3rd Place

Task Rules

  1. Make sure the submission format has met the requirements. See results.zip
  2. Using extra training data are not allowded. But the usage of pretrain model has no limitations.
  3. You have 2 submission chances every week and the counter will be updated at every 00:01, Monday.
  4. The evaluation process takes more than 30 minutes. And a failed submission will not cause the reduction of submission chances.

Task Metric