# Sig2text, a Vision-language model for Non-cooperative Radar Signal Parsing

arXiv: https://arxiv.org/abs/2503.15213 · HTML: https://mlsanity.com/paper/2503.15213/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2025.

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

- [WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment](https://mlsanity.com/paper/2603.22690/) (2026)

## Abstract (arXiv)

Automatic non-cooperative analysis of intercepted radar signals is essential for intelligent equipment in both military and civilian domains. Accurate modulation identification and parameter estimation enable effective signal classification, threat assessment, and the development of countermeasures. In this paper, we propose a symbolic approach for radar signal recognition and parameter estimation based on a vision-language model that combines context-free grammar with time-frequency representation of radar waveforms. The proposed model, called Sig2text, leverages the power of vision transformers for time-frequency feature extraction and transformer-based decoders for symbolic parsing of radar waveforms. By treating radar signal recognition as a parsing problem, Sig2text can effectively recognize and parse radar waveforms with different modulation types and parameters. We evaluate the performance of Sig2text on a synthetic radar signal dataset and demonstrate its effectiveness in recognizing and parsing radar waveforms with varying modulation types and parameters. The training code of the model is available at https://github.com/Na-choneko/sig2text.