XTM-Imaging: Explainable and Trustworthy Multimodal Imaging for Real-World Applications

Dear Colleagues,

Image and video data are at the heart of modern perception systems, powering recognition, diagnosis, inspection, and autonomous decision-making. Increasingly, imaging pipelines are no longer purely visual: they integrate text, audio, time-series sensors, LiDAR/Radar, wireless/RF signals, biomedical signals, and structured knowledge to improve robustness and coverage in real-world settings. However, this multimodal shift introduces a critical barrier for deployment—explainability and trustworthiness. In high-stakes imaging applications such as medical imaging, industrial visual inspection and fault diagnosis, autonomous driving perception, robotics, remote sensing, and affective computing from images/videos, stakeholders require models to provide human-understandable evidence, reliable uncertainty estimates, and verifiable reasoning, not only high accuracy.

This Special Issue focuses on explainable and trustworthy multimodal imaging, where image/video processing remains the central modality and auxiliary modalities are used to support interpretation, calibration, and robust decision-making. We welcome submissions on interpretable multimodal representations for imaging tasks, evidence localization and attribution (e.g., heatmaps, concept-based explanations), uncertainty-aware fusion, causal/counterfactual explanations for vision-centric models, learning under missing/noisy/asynchronous modalities, and evaluation protocols for explanation faithfulness and user-aligned reliability. We also encourage application papers and surveys that demonstrate explainable multimodal imaging systems across real-world domains.

Dr. Xianxun Zhu
Dr. Hui Chen
Dr. Zhangkai Wu
Dr. Hengyu Liu
Dr. Zhihong Cui
Dr. Jianbo Zheng
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• explainable multimodal imaging
• trustworthy image/video understanding
• evidence localization and attribution in vision
• uncertainty estimation and calibration for imaging models
• interpretable image–language / image–sensor fusion
• causal and counterfactual explanations for vision systems
• robust imaging under missing/noisy modalities
• medical imaging decision support
• industrial visual inspection and fault diagnosis
• autonomous driving perception and safety
• human-centered evaluation of explanations