The Drone-vs-Bird Detection Grand Challenge, organized by the WOSDETC consortium, aims at attracting research efforts to identify novel solutions to the problem outlined above, by providing a video dataset that may be difficult to obtain (drone flying requires special conditions and permissions, and shore areas are needed for the considered problem). The challenge goal is to detect a drone appearing at some time in a short video sequence where birds are also present: the algorithm should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds. The dataset is continually increased over consecutive installments of the challenge and made available to the community afterward.

Handling noisy data is a persistent issue in machine learning, but it takes on a unique complexity in the context of graph structures. In domains where graph data is prevalent—such as social networks, biological networks, and financial systems—noisy labels can significantly degrade model performance, leading to unreliable predictions. Despite its significance, this problem is not well-explored. This competition will address this gap investigating graph classification under label noise, driving major advancements in both research and real-world applications.