# MobiAct: Efficient MAV Action Recognition Using MobileNetV4 with Contrastive Learning and Knowledge Distillation

arXiv: https://arxiv.org/abs/2510.19273 · HTML: https://mlsanity.com/paper/2510.19273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [MobileNetV4 -- Universal Models for the Mobile Ecosystem](https://mlsanity.com/paper/2404.10518/) (2024)
- [One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation](https://mlsanity.com/paper/2310.19444/) (2023)
- [SVFormer: Semi-supervised Video Transformer for Action Recognition](https://mlsanity.com/paper/2211.13222/) (2022)
- [VkD: Improving Knowledge Distillation using Orthogonal Projections](https://mlsanity.com/paper/2403.06213/) (2024)
- [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)
- [A Comprehensive Review of Knowledge Distillation in Computer Vision](https://mlsanity.com/paper/2404.00936/) (2024)
- [Generative Model-based Feature Knowledge Distillation for Action Recognition](https://mlsanity.com/paper/2312.08644/) (2023)
- [A Networked Multi-Agent System for Mobile Wireless Infrastructure on Demand](https://mlsanity.com/paper/2306.08737/) (2023)
- [Sample-level Adaptive Knowledge Distillation for Action Recognition](https://mlsanity.com/paper/2504.00606/) (2025)
- [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)
- [Enhancing Action Recognition from Low-Quality Skeleton Data via Part-Level Knowledge Distillation](https://mlsanity.com/paper/2404.18206/) (2024)
- [MAVR-Net: Robust Multi-View Learning for MAV Action Recognition with Cross-View Attention](https://mlsanity.com/paper/2510.15448/) (2025)

## Abstract (arXiv)

Accurate and efficient recognition of Micro Air Vehicle (MAV) motion is essential for enabling real-time perception and coordination in autonomous aerial swarm. However, most existing approaches rely on large, computationally intensive models that are unsuitable for resource-limited MAV platforms, which results in a trade-off between recognition accuracy and inference speed. To address these challenges, this paper proposes a lightweight MAV action recognition framework, MobiAct, designed to achieve high accuracy with low computational cost. Specifically, MobiAct adopts MobileNetV4 as the backbone network and introduces a Stage-wise Orthogonal Knowledge Distillation (SOKD) strategy to effectively transfer MAV motion features from a teacher network (ResNet18) to a student network, thereby enhancing knowledge transfer efficiency. Furthermore, a parameter-free attention mechanism is integrated into the architecture to improve recognition accuracy without increasing model complexity. In addition, a hybrid loss training strategy is developed to combine multiple loss objectives, which ensures stable and robust optimization during training. Experimental results demonstrate that the proposed MobiAct achieves low-energy and low-computation MAV action recognition, while maintaining the fastest action decoding speed among compared methods. Across all three self-collected datasets, MobiAct achieves an average recognition accuracy of 92.12%, while consuming only 136.16 pJ of energy and processing recognition at a rate of 8.84 actions per second. Notably, MobiAct decodes actions up to 2 times faster than the leading method, with highly comparable recognition accuracy, highlighting its superior efficiency in MAV action recognition.