Human-centric Video Matting Challenge
Powered by maadaa.ai open dataset
The outbreak of the coronavirus this past year has accelerated the adoption of video conferencing software. More and more academia, companies and governments are using video conference software for various purposes.Video conference application is enabling a new era for computer vision on research and innovation.
maadaa.ai is working on an open dataset specially designed for video conferencing, to support innovative research, such as setting virtual backgrounds, instance segmentation, sematic segmentation and visual relationship detection.
We are very glad to announce our release of the open dataset for Human-centric video matting (https://fvc-workshop.github.io/challenge.html ), in collaborating with Future Video Conferencing (FVC) at CVPR 2021.
- April 9, 2021 – Start Date
- June 4, 2021 – End Date
We have collected data from various video conferencing APPs on both desktops and mobile phones. Videos are taken indoors (office,home,cafe ect.) and outdoors (park,street,car,train,etc.).
Each video has been trimmed to ~15s using our interactive video segmentation tools.
maadaa.ai is providing this open dataset under the CC BY-NC 4.0 license.
Robotic X Lab and AI Lab
University of Washington
Australian National University
University of Minnesota
Please feel free to contact firstname.lastname@example.org if you have any questions.
Scan the QR code to join the groups.