Using computer vision technology to detect prohibited items in X-ray images is an effective method for realizing intelligent security checking. Dual-view security checking can capture the images from both vertical and horizontal perspectives of the same package at the same time, addressing issues such as unfavorable imaging angles and object occlusion at the image acquisition end. In this paper, we proposed a novel prohibited item detection model based on Transformer architecture in dual-view X-ray images. Two feature fusion module, named as feature selection module and corss-attention fusion module, are introduced to make interaction and enhancement. To improve the model inference efficiency, we use MobileViT as the backbone network to reduce the model size. Simulation results based on Dualray dataset has demonstrated the performance of the proposed model.
This paper presents a theoretical framework for generating and controlling high-dimensional quantum entanglement by harnessing the scattering properties of quantum graphs (QGs). By mapping the three scattering channels of a QG onto the basis states of a quantum three-level system (qutrit), we have successfully extended the entanglement-generation protocol based on the QG from two to three dimensions. A novel triple-controlled scattering operator is introduced, which enables the conditional reconfiguration of Bob’s QG based on the scattering outcome of Alice’s. Through rigorous theoretical derivation, we establish the precise analytical conditions under which the composite system resides in either a maximally entangled or a separable state. Our findings indicate that achieving maximal entanglement requires the simultaneous satisfaction of two conditions. First, the scattering entropy of Alice’s QG must be maximal, meaning that the exit probability through each of its three channels is equal to . Second, the three conditional output states prepared by Bob must be mutually orthogonal. Finally, we demonstrate that tunable phases can be employed to regulate the degree of entanglement actively, thereby verifying the feasibility and controllability of the proposed framework for high-dimensional quantum information processing.
As multi-view datasets expand across diverse practical fields, feature selection (FS) has become an indispensable preparatory stage for machine learning models. Nevertheless, real-world multi-view data is often unlabeled and distributed among isolated clients, posing significant challenges to traditional centralized methods due to privacy concerns and communication constraints. Furthermore, existing centralized and federated approaches frequently suffer from entrapment in local optima and lack robust convergence guarantees. To address these issues, we propose Fed-MUFSHT, a federated framework for multi-view unsupervised FS (MUFS) that integrates tensor learning with a novel metaheuristic optimizer, Hierarchical-Cognitive Tianji’s Horse Racing Optimization (HC-THRO). Within the federated learning paradigm, Fed-MUFSHT follows a dual-stage local optimization process. Stage 1 applies HC-THRO, which integrates Hierarchical Competitive Learning and Adaptive Cognitive Mapping to simulate multi-level strategic competition and cognitive adaptation among individuals. This design enhances global exploration, adaptive learning, and fine-grained feature selection in high-dimensional spaces. Stage 2 employs a TL module based on canonical polyadic (CP) decomposition to perform missing-view imputation and refine latent representation learning. At the global level, a privacy-preserving aggregation strategy based on Normalized Mutual Information (NMI) and feature weights enables efficient model coordination without exposing raw data. Comparative experiments on several public benchmark datasets reveal that Fed-MUFSHT maintains clear advantages over strong competing methods, showing better optimization results together with more dependable convergence characteristics. The overall evidence suggests that the proposed approach is both robust and effective for distributed optimization tasks involving privacy protection.
Private Set Intersection (PSI) is a crucial Secure Multi-Party Computation (SMPC) primitive which enables participants to securely obtain the intersection