The Grand Challenge on Multimedia Verification is an open competition where researchers and practitioners compete to verify the authenticity and context of multimedia content, addressing real-world misinformation challenges. Participants analyze provided images and videos, assess sources, detect manipulations, and submit a detailed verification report.
In addition to the main task, participants can also take part in the OOC Subtask (Out-of-Context Detection), which focuses on identifying whether multimedia content has been misused in an incorrect or misleading context. This subtask continues the work from the Grand Challenge on Detecting Cheapfakes, previously held at ACM MMSys 2021, ACM MM 2022, IEEE ICME 2023, and ACM ICMR 2024.
There are no restrictions on methodology: solutions can be fully manual, fully automated, or a mix of OSINT, existing tools, and newly developed techniques.
Participants can choose to:
- Compete in the main task.
- Compete in the OOC Subtask only.
- Compete in both the main task and the OOC Subtask.
Additionally, as part of the main task, participants may provide a concise verification summary for general readers. This component is optional and will be evaluated separately based on the main task results.
The competition consists of three stages: Training, Validation, and Real-World Verification. Participants first explore 100 50 known cases to familiarize themselves with the tasks. In the Validation stage, they must analyze 20 10 new cases and pass an evaluation to qualify for the Real-World Verification Stage, where 10 live verification cases will test their methods on fresh, evolving misinformation challenges.
Recognition & Awards. Teams submitting a scientific paper may present at ACM Multimedia, subject to peer review. Only paper-submitting teams are eligible for awards, but all participants’ scores will be officially recognized.
Note: To ensure the quality and accuracy of the cases, we have reduced the number of samples and only provide the high-quality ones.
