# MAVR-Net: Robust Multi-View Learning for MAV Action Recognition with Cross-View Attention

arXiv: https://arxiv.org/abs/2510.15448 · HTML: https://mlsanity.com/paper/2510.15448/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 17 Oct 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [SVFormer: Semi-supervised Video Transformer for Action Recognition](https://mlsanity.com/paper/2211.13222/) (2022)
- [Video Object Segmentation and Tracking: A Survey](https://mlsanity.com/paper/1904.09172/) (2019)
- [Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2008.11901/) (2020)
- [Modality Shifting Attention Network for Multi-modal Video Question Answering](https://mlsanity.com/paper/2007.02036/) (2020)
- [MVFNet: Multi-View Fusion Network for Efficient Video Recognition](https://mlsanity.com/paper/2012.06977/) (2020)
- [Collaborative Spatio-temporal Feature Learning for Video Action Recognition](https://mlsanity.com/paper/1903.01197/) (2019)
- [A Survey of Air-to-Ground Propagation Channel Modeling for Unmanned Aerial Vehicles](https://mlsanity.com/paper/1801.01656/) (2018)
- [Advances in UAV Avionics Systems Architecture, Classification and Integration: A Comprehensive Review and Future Perspectives](https://mlsanity.com/paper/2501.00856/) (2025)
- [A Networked Multi-Agent System for Mobile Wireless Infrastructure on Demand](https://mlsanity.com/paper/2306.08737/) (2023)
- [GPS-denied Navigation: Attitude, Position, Linear Velocity, and Gravity Estimation with Nonlinear Stochastic Observer](https://mlsanity.com/paper/2104.09920/) (2021)
- [MoCom: Motion-based Inter-MAV Visual Communication Using Event Vision and Spiking Neural Networks](https://mlsanity.com/paper/2510.14770/) (2025)
- [Power Efficient Visible Light Communication (VLC) with Unmanned Aerial Vehicles (UAVs)](https://mlsanity.com/paper/1905.04200/) (2019)

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

- [MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation](https://mlsanity.com/paper/2510.19273/) (2025)

## Abstract (arXiv)

Recognizing the motion of Micro Aerial Vehicles (MAVs) is crucial for enabling cooperative perception and control in autonomous aerial swarms. Yet, vision-based recognition models relying only on RGB data often fail to capture the complex spatial temporal characteristics of MAV motion, which limits their ability to distinguish different actions. To overcome this problem, this paper presents MAVR-Net, a multi-view learning-based MAV action recognition framework. Unlike traditional single-view methods, the proposed approach combines three complementary types of data, including raw RGB frames, optical flow, and segmentation masks, to improve the robustness and accuracy of MAV motion recognition. Specifically, ResNet-based encoders are used to extract discriminative features from each view, and a multi-scale feature pyramid is adopted to preserve the spatiotemporal details of MAV motion patterns. To enhance the interaction between different views, a cross-view attention module is introduced to model the dependencies among various modalities and feature scales. In addition, a multi-view alignment loss is designed to ensure semantic consistency and strengthen cross-view feature representations. Experimental results on benchmark MAV action datasets show that our method clearly outperforms existing approaches, achieving 97.8%, 96.5%, and 92.8% accuracy on the Short MAV, Medium MAV, and Long MAV datasets, respectively.