Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.20530 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908493941833728 |
|---|---|
| author | Liu, Wenxuan Zhou, Zhuo Jia, Xuemei Yang, Siyuan Huang, Wenxin Zhong, Xian Lin, Chia-Wen |
| author_facet | Liu, Wenxuan Zhou, Zhuo Jia, Xuemei Yang, Siyuan Huang, Wenxin Zhong, Xian Lin, Chia-Wen |
| contents | Action recognition in unmanned aerial vehicles (UAVs) poses unique challenges due to significant view variations along the vertical spatial axis. Unlike traditional ground-based settings, UAVs capture actions at a wide range of altitudes, resulting in considerable appearance discrepancies. We introduce a multi-view formulation tailored to varying UAV altitudes and empirically observe a partial order among views, where recognition accuracy consistently decreases as altitude increases. This observation motivates a novel approach that explicitly models the hierarchical structure of UAV views to improve recognition performance across altitudes. To this end, we propose the Partial Order Guided Multi-View Network (POG-MVNet), designed to address drastic view variations by effectively leveraging view-dependent information across different altitude levels. The framework comprises three key components: a View Partition (VP) module, which uses the head-to-body ratio to group views by altitude; an Order-aware Feature Decoupling (OFD) module, which disentangles action-relevant and view-specific features under partial order guidance; and an Action Partial Order Guide (APOG), which uses the partial order to transfer informative knowledge from easier views to more challenging ones. We conduct experiments on Drone-Action, MOD20, and UAV, demonstrating that POG-MVNet significantly outperforms competing methods. For example, POG-MVNet achieves a 4.7% improvement on Drone-Action and a 3.5% improvement on UAV compared to state-of-the-art methods ASAT and FAR. Code will be released soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer Liu, Wenxuan Zhou, Zhuo Jia, Xuemei Yang, Siyuan Huang, Wenxin Zhong, Xian Lin, Chia-Wen Computer Vision and Pattern Recognition Action recognition in unmanned aerial vehicles (UAVs) poses unique challenges due to significant view variations along the vertical spatial axis. Unlike traditional ground-based settings, UAVs capture actions at a wide range of altitudes, resulting in considerable appearance discrepancies. We introduce a multi-view formulation tailored to varying UAV altitudes and empirically observe a partial order among views, where recognition accuracy consistently decreases as altitude increases. This observation motivates a novel approach that explicitly models the hierarchical structure of UAV views to improve recognition performance across altitudes. To this end, we propose the Partial Order Guided Multi-View Network (POG-MVNet), designed to address drastic view variations by effectively leveraging view-dependent information across different altitude levels. The framework comprises three key components: a View Partition (VP) module, which uses the head-to-body ratio to group views by altitude; an Order-aware Feature Decoupling (OFD) module, which disentangles action-relevant and view-specific features under partial order guidance; and an Action Partial Order Guide (APOG), which uses the partial order to transfer informative knowledge from easier views to more challenging ones. We conduct experiments on Drone-Action, MOD20, and UAV, demonstrating that POG-MVNet significantly outperforms competing methods. For example, POG-MVNet achieves a 4.7% improvement on Drone-Action and a 3.5% improvement on UAV compared to state-of-the-art methods ASAT and FAR. Code will be released soon. |
| title | Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.20530 |