Blind face restoration (BFR) aims to recover high-quality (HQ) facial images from degraded inputs with unknown distortions, while preserving identity consistency. Existing methods either rely solely on visual priors or incorporate generic textual cues, struggle with noise sensitivity or insufficient semantic guidance. In this paper, we present a vision-language guided BFR framework that consists of three key components: (1) a Facial Key Attribute Estimation module that leverages structured text to compactly describe facial attributes; (2) a Dual-modal Based Latent Prediction module built on a shared-attention Transformer, which fuses visual and textual embeddings to predict dictionary elements representing the target face; (3) a Text-based Adaptive Feature Filter that dynamically suppresses noise in skip-connected features by aligning them with textual semantics, enhancing the generator’s ability to leverage multi-scale spatial information. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches on multiple benchmarks, particularly under severe degradation.

Gait recognition has emerged as a crucial biometric technique because it enables unobtrusive and remote identification. However, silhouette-based methods are often affected by variations in clothing and carrying conditions. To address these challenges, we propose a novel multi-modal approach that integrates Gait Energy Images (GEI) and Skeletal Gait Energy Images (SkeGEI) to enhance recognition performance. GEIs capture appearance-based holistic motion patterns, while SkeGEIs, generated from normalized skeletal representations centred on the neck joint, provide robust structural features. Skeletal coordinates are extracted using HRNet for the CASIA-B dataset and AlphaPose for the OU-MVLP dataset, which are then used to generate SkeGEIs. Our composite fusion model effectively combines GEI and SkeGEI features through Cross-Alignment blocks (CAB), attention mechanisms, and Progressive Fusion Blocks (PFB). Extensive evaluations on the CASIA-B and OU-MVLP datasets demonstrate that the proposed approach achieves superior performance compared to state-ofthe- art methods across diverse conditions. However, the model struggles with crossdataset generalization, particularly in varied clothing conditions. Additionally, an ablation study highlights the effectiveness of each component, validating the superiority of our integrated model.

This paper presents a novel halftoning algorithm based on continuous relaxation and gradient-based optimization. By reformulating the original binary quadratic programming (BQP) problem into a differentiable non-convex objective, the proposed method integrates a perceptual loss with a binarization regularizer to guide the optimization toward high-quality binary outputs. Unlike deep learning-based approaches, our method is model-free, memory-efficient, and fully interpretable, enabling fast convergence without complex training or large memory overhead. Experimental results demonstrate that the proposed method outperforms both classical and neural halftoning techniques in terms of image quality and convergence speed. This work provides a practical and scalable solution for highresolution halftone image generation, particularly suitable for industrial and real-time applications under resource constraints.

The rapid rise in the amount of medical data poses a significant challenge for researchers in preventing its manipulation. To overcome this prevalent challenge in the healthcare field, this proposed work introduces a dual-image watermarking framework. This method embeds two secret images into a host image. The proposed framework uses Higher Order Singular Value Decomposition (HOSVD), Non-Subsampled Shearlet Transform (NSST), and a 12-layer deep neural network. The results indicate high imperceptibility, robustness against attacks, and superior capacity compared to existing techniques.

Multi-access Edge Computing (MEC) enhances user experience by caching content at nearby base stations or edge servers, thereby reducing repetitive data retrieval and latency. However, edge servers face challenges such as high data storage costs and stringent network requirements, which conflict with their limited performance capabilities. To address these issues, cooperative caching among servers has emerged as a pivotal research area. In this paper, we first establish a model that links the quality of experience (QoE) with the quality of service (QoS). Then, queuing theory is used to estimate the impact of access rate on QoE. Second, we describe the server file caching decision issue as a type of extensive game problem. Finally, we propose an improved discrete binary particle swarm optimization (BPSO) algorithm to solve the optimal decision. Simulation results indicate that our algorithm ensures a higher hit rate and achieves the highest QoE compared to existing algorithms.