Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.19640 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915922970673152 |
|---|---|
| author | Chang, Hao Wang, Zhihui Wu, Lingxiang An, Wei Li, Boyang Lin, Zaiping Sheng, Weidong Wang, Jinqiao |
| author_facet | Chang, Hao Wang, Zhihui Wu, Lingxiang An, Wei Li, Boyang Lin, Zaiping Sheng, Weidong Wang, Jinqiao |
| contents | Low-altitude vision systems are becoming a critical infrastructure for smart city governance. However, existing object-centric perception paradigms and loosely coupled vision-language pipelines are still difficult to support management-oriented anomaly understanding required in real-world urban governance. To bridge this gap, we introduce GovLA-10K, the first management-oriented multi-modal benchmark for low-altitude intelligence, along with GovLA-Reasoner, a unified vision-language reasoning framework tailored for governance-aware aerial perception. Unlike existing studies that aim to exhaustively annotate all visible objects, GovLA-10K is deliberately designed around functionally salient targets that directly correspond to practical management needs, and further provides actionable management suggestions grounded in these observations. To effectively coordinate the fine-grained visual grounding with high-level contextual language reasoning, GovLA-Reasoner introduces an efficient Spatially-aware Grounding Adapter (SGA) that implicitly coordinates discriminative representation sharing between the visual detector and the large language model (LLM). Different from existing adapters that primarily focus on global embedding alignment, our SGA is specifically designed to compress and aggregate multi-stream grounding-aware representations, thereby preserving fine-grained spatial cues while enabling their effective integration into the language reasoning process. Extensive experiments indicate that our GovLA-Reasoner effectively improves performance while avoiding the need of fine-tuning for any task-specific individual components. We believe our work offers a new perspective and foundation for future studies on management-aware low-altitude vision-language systems. The code and dataset will be publicly released after further organization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19640 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Focus on What Really Matters in Low-Altitude Governance: A Management-Centric Multi-Modal Benchmark with Implicitly Coordinated Vision-Language Reasoning Framework Chang, Hao Wang, Zhihui Wu, Lingxiang An, Wei Li, Boyang Lin, Zaiping Sheng, Weidong Wang, Jinqiao Computer Vision and Pattern Recognition Low-altitude vision systems are becoming a critical infrastructure for smart city governance. However, existing object-centric perception paradigms and loosely coupled vision-language pipelines are still difficult to support management-oriented anomaly understanding required in real-world urban governance. To bridge this gap, we introduce GovLA-10K, the first management-oriented multi-modal benchmark for low-altitude intelligence, along with GovLA-Reasoner, a unified vision-language reasoning framework tailored for governance-aware aerial perception. Unlike existing studies that aim to exhaustively annotate all visible objects, GovLA-10K is deliberately designed around functionally salient targets that directly correspond to practical management needs, and further provides actionable management suggestions grounded in these observations. To effectively coordinate the fine-grained visual grounding with high-level contextual language reasoning, GovLA-Reasoner introduces an efficient Spatially-aware Grounding Adapter (SGA) that implicitly coordinates discriminative representation sharing between the visual detector and the large language model (LLM). Different from existing adapters that primarily focus on global embedding alignment, our SGA is specifically designed to compress and aggregate multi-stream grounding-aware representations, thereby preserving fine-grained spatial cues while enabling their effective integration into the language reasoning process. Extensive experiments indicate that our GovLA-Reasoner effectively improves performance while avoiding the need of fine-tuning for any task-specific individual components. We believe our work offers a new perspective and foundation for future studies on management-aware low-altitude vision-language systems. The code and dataset will be publicly released after further organization. |
| title | Focus on What Really Matters in Low-Altitude Governance: A Management-Centric Multi-Modal Benchmark with Implicitly Coordinated Vision-Language Reasoning Framework |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.19640 |