U${}^2$-Revisit: Persistent Event Reasoning under Intermittent Aerial Revisits

Route-based UAV inspection efficiently covers spatially distributed regions but observes each location only intermittently, with irregular gaps during which the region state remains unobserved. Verifying persistent events therefore requires reasoning across revisits while distinguishing confirmed absence from missing or unreliable evidence. A region-centered benchmark and a coarse-to-fine pipeline are introduced for this setting. Fixed semantic map regions provide spatial correspondence across revisits, and a lightweight proposal stage identifies candidate sequences for a learned multi-revisit verifier. U${}^2$-Revisit combines visual, telemetry, map, and observation-quality information through quality-aware fusion. Separate spatial and instance memories represent region state and vehicle-related evidence. Under a seven-fold, site-ID-disjoint LOSO protocol, U${}^2$-Revisit achieves the highest mean Event AP of $0.9594\pm 0.0082$ across three seeds. Single Revisit and Unordered Set achieve $0.8840\pm 0.0380$ and $0.9462\pm 0.0270$, respectively. Repeated-observation aggregation accounts for most of the Event AP improvement over Single Revisit, and U${}^2$-Revisit further improves Event AP beyond Unordered Set.