In satellite-based tactical communication systems, non-cooperative radio frequency (RF) communication signals are widely used, but their detection remains highly challenging in complex electromagnetic environments characterized by low signal-to-noise ratios, multi-signal coexistence, and dynamic interference. This paper focuses on the most widely used non-cooperative communication protocols—Link 11 and Link 4A—and proposes a cross-modal detection approach that maps signals into the image domain through high-resolution time-frequency analysis, enhancing detection robustness and interpretability. Additionally, we construct SC2SM, the first benchmark dataset specifically designed for communication signal detection, comprising 14,791 time-frequency images and over 85,000 annotated bounding boxes, comprehensively covering aliasing, strong interference, and other complex environmental scenarios. Furthermore, we introduce YOLO-Link, the first optimized object detection framework for this task, which enables efficient deployment on Internet of Things (IoT) edge computing platforms. Extensive experimental results demonstrate that, after training on the SC2SM dataset, YOLO-Link achieves state-of-the-art performance in communication signal detection, outperforming existing methods by 4.1% in Recall and achieving real-time inference at 40 FPS on IoT edge computing platforms, striking an optimal balance between detection accuracy and computational efficiency. This study provides technical support for intelligent detection and monitoring of non-cooperative communication signals and promotes the application of cross-modal learning in complex electromagnetic environments. The code and dataset are available at.

Recent restoration methods for handling real old photos have achieved significant improvements using generative networks. However, the restoration quality under the usual generative architectures is greatly affected by the encoded properties of latent space, which reflect pivotal semantic information in the recovery process. Therefore, how to find the suitable latent space and identify its semantic factors is an important issue in this challenging task. To this end, we propose a novel generative network with hyperbolic embeddings to restore old photos that suffer from multiple degradations. Specifically, we transform high-dimensional Euclidean features into a compact latent space via the hyperbolic operations. In order to enhance the hierarchical representative capability, we perform the channel mixing and group convolutions for the intermediate hyperbolic features. By using attention-based aggregation mechanism in a hyperbolic space, we can further obtain the resulting latent vectors, which are more effective in encoding the important semantic factors and improving the restoration quality. Besides, we design a diversity loss to guide each latent vector to disentangle different semantics. Extensive experiments have shown that our method is able to generate visually pleasing photos and outperforms state-of-the-art restoration methods.

Image inpainting refers to synthesizing plausible contents for images with missing regions. However, current methods often create blurry textures, distorted structures and loss of details, especially when the image has complex scenes or large missing regions. We propose a fine-grained adversarial image inpainting model with super resolution. It performs a coarse-to-fine inpainting procedure in two stages. The proposed generator first synthesizes initial predictions of the missing regions with a novel encoder-decoder structure. Then it refines the predicted missing regions by generating high-frequency details via super resolution. We evaluate the proposed from both pixel level and semantic level. Experiments demonstrate that the proposed can generate higher quality inpainting results than the baseline models in both metrics.