FALCON：面向未来的学习与基于上下文的对象中心预训练用于无人机动作识别
FALCON: Future-Aware Learning with Contextual Object-Centric Pretraining for UAV Action Recognition
AI总结：
FALCON通过结合对象感知的遮蔽自动编码和对象中心双时间线未来重建，提升无人机动作识别的准确率和推理速度。
摘要：
我们介绍了FALCON，一种统一的自监督视频预训练方法，用于从原始RGB高空视频中进行无人机动作识别，无需在推理时进行额外预处理。无人机视频存在严重的空间不平衡：大而杂乱的背景主导视野，导致基于重建的预训练在无信息区域浪费容量，并且学习人类/物体线索不足。FALCON通过整合对象感知的遮蔽自动编码与对象中心双时间线未来重建来解决这一问题。在预训练期间仅使用检测来构建对象性先验，使（i）在遮蔽期间保持令牌可视性平衡，（ii）将重建监督集中在与动作相关区域，防止学习被背景外观主导。为进一步促进时间动态学习，我们进一步在对象中心监督区域内重建短和长时间线的未来内容，在嘈杂的高空上下文中注入具有鲁棒性的前瞻性时间监督。在无人机基准测试中，FALCON在使用ViT-B主干的情况下，NEC-Drone的Top-1准确率提高了2.9%，UAV-Human提高了5.8%，同时比依赖重测试时间增强的监督方法快2-5倍。
英文摘要：
We introduce FALCON, a unified self-supervised video pretraining approach for UAV action recognition from raw RGB aerial footage, requiring no additional preprocessing at inference. UAV videos exhibit severe spatial imbalance: large, cluttered backgrounds dominate the field of view, causing reconstruction-based pretraining to waste capacity on uninformative regions and under-learn action-relevant human/object cues. FALCON addresses this by integrating object-aware masked autoencoding with object-centric dual-horizon future reconstruction. Using detections only during pretraining, we construct objectness priors that (i) enforce balanced token visibility during masking and (ii) concentrate reconstruction supervision on action-relevant regions, preventing learning from being dominated by background appearance. To promote temporal dynamics learning, we further reconstruct short- and long-horizon future content within an object-centric supervision region, injecting anticipatory temporal supervision that is robust to noisy aerial context. Across UAV benchmarks, FALCON improves top-1 accuracy by 2.9\% on NEC-Drone and 5.8\% on UAV-Human with a ViT-B backbone, while achieving 2$\times$--5$\times$ faster inference than supervised approaches that rely on heavy test-time augmentation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
