AURA: Uncovering Anomalous Events for Marine Environmental Monitoring via Visual Anomaly Detection

AURA: Anomalous Underwater Reef Activity The first multi-annotator benchmark dataset for visual anomaly detection in underwater scenes, published at ICCV 2025. This dataset contains 25 underwater videos from two marine locations in Denmark with annotated anomalous events (fish, crabs, and biological activity). Each video was annotated by 16 people, providing soft labels that capture annotation uncertainty and consensus event boundaries for temporal evaluation. Key Features: - 25 videos (10 from Scene A - Hundested Harbour, 15 from Scene B - Limfjords-bridge)- 15,083 total frames with frame-level soft labels- 16 annotators per video capturing subjective nature of "interesting" events- Multi-annotator consensus labels for event boundaries- Two distinct underwater scenes with different visual characteristics Scene A Normal - Anomalous Scene B Normal - Anomalous The dataset supports research in visual anomaly detection, particularly for applications in marine environmental monitoring and biodiversity assessment. Full paper available here. In case you use this dataset, please add a citation:Weihl, L., Bengtson, S.H., Novak, N., & Pedersen, M. (2025). Uncovering Anomalous Events for Marine Environmental Monitoring via Visual Anomaly Detection. ICCV Workshops, 2085-2094.