ACM Multimedia 2020 Grand Challenge – Video Relation Understanding
We are hosting a grand challenge on Video Relation Understanding (VRU) at the ACM Multimedia 2020 conference. The purpose of this challenge is to push video content analysis at the relational and structural level, which is a future scheme of the next AI-powered multimedia systems.
This year’s challenge encourages participants to explore and develop innovative models to detect object entities, along with their relationships, in a given video. Specifically, all participants will join the main task of Visual Relation Detection and can also submit for the optional task, Video Object Detection. The submissions will be evaluated using Mean Average Precision metrics on a large-scale video dataset, VidOR. We hope that these tasks can advance the foundation of future systems capable of performing complex inferences, and further bridge the gap between vision and language.
To find out more about this grand challenge and how to register, visit the link below:
Event period: March 10 – July 8, 2020
- March 31, 2020: Precomputed features and trajectories release
- April 29, 2020: Registration close and submission server fully open
- May 29, 2020: Testing videos release to the registered participants
- June 29, 2020, 23:59 AoE: submission server close
- July 1, 2020: Final evaluation results announce on the website