ACAD Research
Our Youtube Channel
Learn about our work on artificial intelligence / computer vision / deep learning, through dynamic, (hopefully) entertaining and (hopefully) understandable scientific videos!
We are deep learning enthusiast Post-Doc researchers at the University of Liège (Belgium -- that’s a small kingdom in Europe, just in case).
Featured videos
SoccerNet 2024: Return of the Challenges!
Join the SoccerNet community and take part in the 2024 challenges in soccer video analysis. Be part of the research community pushing the boundaries of broadcast, field, and player understanding. With new tasks and challenges, including fine-grained ball action spotting, dense video captioning, multi-view foul recognition, and game state reconstruction, there's a challenge for everyone. With prizes for each challenge and a chance to be recognized at CVPR, start your journey now and help shape the future of soccer video analysis. Join our Discord community, follow us on social media, and be sure to leave a like and subscribe to our channel for updates. Let's get started!
Be the Champion of Soccer AI: Join the SoccerNet 2023 Challenges Now!
Join the SoccerNet community and take part in the 2023 challenges in soccer video analysis. Be part of the research community pushing the boundaries of broadcast, field, and player understanding. With new tasks and challenges, including fine-grained action spotting, dense video captioning, and jersey number recognition, there's a challenge for everyone. With prizes for each challenge and a chance to be recognized at CVPR, start your journey now and help shape the future of soccer video analysis. Join our Discord community, follow us on social media, and be sure to leave a like and subscribe to our channel for updates. Let's get started!
Semi-Supervised Learning to Improve Detections
In this video, we present our latest paper: “Semi-Supervised Training To Improve Player and Ball Detection in Soccer” published at the CVPR 2022 workshop CVsports. This work introduces a semi-supervised learning method to improve the object detection using a large amount of unlabeled data. Particularly, we tackle object detection from satellite images and soccer videos.
Soccer Player Tracking, Re-ID, Camera Calibration and Action Spotting - SoccerNet Challenges 2022
In this video, we present our new SoccerNet Challenges for CVPR 2022! We introduce the three tasks of Calibration, Re-identification and Tracking on soccer games, in partnership with EVS Broadcast Equipment, SportRadar and Baidu Research. We also reiterate our previous Action Spotting and Replay Grounding Challenges at the ActivityNet workshop. Good luck fighting for the throne!