{"id":697528,"date":"2025-10-31T06:35:43","date_gmt":"2025-10-31T03:35:43","guid":{"rendered":"https:\/\/buradabiliyorum.com\/en\/researchers-advance-cross-modality-smart-security-with-transformer-model\/"},"modified":"2025-10-31T06:35:43","modified_gmt":"2025-10-31T03:35:43","slug":"researchers-advance-cross-modality-smart-security-with-transformer-model","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/researchers-advance-cross-modality-smart-security-with-transformer-model\/","title":{"rendered":"Researchers advance cross-modality smart security with transformer model"},"content":{"rendered":"
\n
\n
\n
\n \"Researchers
\n Illustration of the VX-ReID task and main idea. Credit: Wang Hongqiang
\n <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n

A research team led by Professor Wang Hongqiang from the Hefei Institutes of Physical Science<\/a> of the Chinese Academy of Sciences proposed a Global-Local Alignment Attention (GLAA) model based on an Asymmetric Siamese Transformer (AST), which markedly enhances the performance of Visible-X-ray cross-modality package re-identification tasks.<\/p>\n

This study was published in IEEE Transactions on Information Forensics and Security<\/i><\/a>.<\/p>\n

Visible X-ray cross-modality package re-identification is a core technology<\/a> in security inspection. The challenge lies in the significant pixel-level differences between the two modal images, making it difficult for traditional methods to extract robust cross-modality invariant features.<\/p>\n

In this study, the researchers incorporated an asymmetric design concept into the Siamese Transformer architecture by proposing a Cross-Modality Asymmetric Siamese Transformer (CAST) structure. Embedding LayerNorm layers and modality-aware encoding in one branch effectively enhances the model’s ability to extract cross-modality invariant features.<\/p>\n

They also designed a Global-Local Cross-modality Alignment Attention module. By modeling the interaction between global and local features, it enhances fine-grained feature representation while addressing the spatial misalignment issues in cross-modality images.<\/p>\n

Experimental results show that the key metrics of this model on a dedicated cross-modality package re-identification dataset show significant improvement over the current state-of-the-art methods, providing reliable technical support for the intelligentization of security inspection.<\/p>\n

This work is the first to introduce the Transformer architecture into the cross-modality package re-identification task, breaking through the limitations of existing methods that rely on symmetric convolutional networks, according to the researchers.<\/p>\n

\n

More information:<\/strong>
\n\t\t\t\t\t\t\t\t\t\t\t\tYonggan Wu et al, An Asymmetric Siamese Transformer With Global-Local Alignment Attention for Visible-X-Ray Cross-Modality Package Re-Identification, IEEE Transactions on Information Forensics and Security<\/i> (2025). DOI: 10.1109\/tifs.2025.3592540<\/a><\/p>\n<\/div>\n

\n Provided by
\n Chinese Academy of Sciences
\n \t\t\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/svg>
\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/a><\/p><\/div>\n

<\/p>\n

\n

\n Citation<\/strong>:
\n Researchers advance cross-modality smart security with transformer model (2025, October 30)
\n retrieved 30 October 2025
\n from https:\/\/techxplore.com\/news<\/a>\/2025-10-advance-modality-smart.html\n <\/p>\n

\n This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
\n part may be reproduced without the written permission. The content is provided for information purposes only.\n <\/p>\n<\/p><\/div>\n<\/p><\/div>\n