The paper introduces the Wide-area Spatio-temporal Scene Understanding (WSTU) problem, which demands simultaneous wide-area coverage, per-target resolution, and temporal continuity—capabilities lacking in existing datasets. To address this, the authors present HARD, an ultra‑high‑resolution (12768×9564) UAV dataset annotated for object detection, multi‑object tracking, and scene‑level visual question answering. They also propose a latency‑aware metric, streaming‑HOTA (s‑HOTA), and show through baseline experiments that high resolution and processing latency significantly impact detection, tracking, and VQA performance, revealing gaps in current methods for WSTU.
arXiv:2609.09396v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance toward physical deployment, the focus has remained on action-oriented Embodied AI evaluated on subject-centric...
arXiv:2606. 27876v1 Announce Type: cross Abstract: Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation.
The paper introduces NWPU-Refer, the largest bilingual dataset for referring remote sensing image segmentation, featuring 15,003 high‑resolution images from over 30 countries and 49,745 annotated targets. It also proposes the Multi‑scale Referring Segmentation Network (MRSNet), which uses an Intra‑scale Feature Interaction Module to refine fine‑grained features and a Hierarchical Feature Interaction Module to fuse cross‑scale information while preserving spatial structure. Experiments on NWPU‑Refer and RRSIS‑D show that MRSNet achieves strong, competitive performance, especially under strict IoU thresholds, demonstrating the effectiveness of both the new dataset and the model.
AerialDojo-200K is a large-scale benchmark suite for open-world aerial object-goal search, featuring 42 simulation scenes across four families and 21 types, including urban, natural, infrastructure, and disaster environments. The dataset contains 205,732 task instances—over 100K semantic-goal and over 100K image-goal tasks—each with a collision-free reference trajectory and multi-view video recordings. A unified evaluation framework splits scenes into 21 in-distribution and 21 out-of-distribution sets, and preliminary tests on multimodal large language models show significant room for improvement in general-purpose aerial agents.
Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployment, the UAV must respond while it flies, so such perception runs in an online streaming manner, where frames arrive sequentially and the model responds to each one without access to future frames.
arXiv:2607. 19857v1 Announce Type: cross Abstract: Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes.
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
Event cameras offer microsecond-level temporal resolution and high dynamic range for low-altitude UAV perception. However, long-range UAVs often produce sparse, fragmented, and noise-contaminated event responses, where one semantic target may appear as multiple spatially separated blobs.
arXiv:2607. 08359v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs.
arXiv:2610.40801v1 Announce Type: new Abstract: The reasoning capabilities of vision-language models (VLMs) can be limited by incomplete or inaccurate visual observations in the general domain. In un...
LEVIRDet-159 is the largest remote sensing object detection dataset, featuring 159 categories, 2.56 million bounding boxes, and 700k fine‑grained annotations across a multi‑level taxonomy. It surpasses existing datasets by roughly 7× more images, 6× more object instances, and 4× more categories. Leveraging this dataset, the authors propose LEVIRDetNet, a scale‑hierarchy‑aware foundation model that predicts ground sampling distance, modulates queries accordingly, and employs a hierarchy‑aware detection head, achieving state‑of‑the‑art performance on nine external benchmarks without target‑domain training or fine‑tuning.
SatNav is a new, scalable benchmark for long‑horizon vision‑language navigation (VLN) with unmanned aerial vehicles (UAVs), built from high‑resolution satellite imagery. It generates 118,000 navigation episodes across 59 scenes in 18 cities, using satellite crops to approximate UAV nadir views and featuring three task families—Boundary, Landmark, and Route—to test long‑term memory and geospatial reasoning. The benchmark also introduces SwiftVLN, a modular framework for memory component experimentation, and demonstrates that models trained on satellite data can transfer to real‑flight UAV observations.