# Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer

arXiv: https://arxiv.org/abs/2504.20530 · HTML: https://mlsanity.com/paper/2504.20530/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Gibbs Sampling with People](https://mlsanity.com/paper/2008.02595/) (2020)
- [UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition](https://mlsanity.com/paper/1901.02602/) (2019)
- [DVANet: Disentangling View and Action Features for Multi-View Action Recognition](https://mlsanity.com/paper/2312.05719/) (2023)
- [Action Recognition for Depth Video using Multi-view Dynamic Images](https://mlsanity.com/paper/1806.11269/) (2018)
- [TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device](https://mlsanity.com/paper/2109.13227/) (2021)
- [Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization](https://mlsanity.com/paper/2304.08799/) (2023)
- [3D CNNs with Adaptive Temporal Feature Resolutions](https://mlsanity.com/paper/2011.08652/) (2020)
- [Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models](https://mlsanity.com/paper/2203.16755/) (2022)
- [Learning a Deep Model for Human Action Recognition from Novel Viewpoints](https://mlsanity.com/paper/1602.00828/) (2016)
- [A Multi-viewpoint Outdoor Dataset for Human Action Recognition](https://mlsanity.com/paper/2110.04119/) (2021)
- [PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition](https://mlsanity.com/paper/2304.06866/) (2023)
- [Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning](https://mlsanity.com/paper/2303.00396/) (2023)
- [Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning](https://mlsanity.com/paper/2308.15169/) (2023)
- [FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification](https://mlsanity.com/paper/2209.11316/) (2022)

## Built on by (most cited first, 1 of 1)

- [Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey](https://mlsanity.com/paper/2510.09731/) (2025)

## Abstract (arXiv)

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.