The centralized high-power jamming has the limitations，such as restricted coverage and susceptibility to localization，in modern communication countermeasures.This paper presents a distributed jamming signal recognition method based on an air-sea integrated framework.The proposed method is to use the unmanned aerial vehicles to collect the jamming signals，while a maritime information center conducts multi-source fusion and feature extraction.A multi-stage Vision Transformer (ViT) model with multi-dimensional signal representation，is then designed for the recognition and classification of jamming signals.Experimental results show that the proposed method achieves higher recognition accuracy and efficiency than the conventional methods，while maintaining robustness under low signal-to-noise ratios and diverse interference scenarios.These results demonstrate the method’s adaptability to complex environments and its potential to support rapid decision-making in modern battlefields.This study provides a feasible path for the engineering application of distributed communication jamming technologies and establishes a technical basis for the development of air-sea integrated electronic countermeasure systems.