期刊名：AI
期刊主页：https://www.mdpi.com/journal/ai
计算机视觉与图像处理正从“单模态识别”向“多模态理解、可解释诊断与跨域泛化”的范式演进。本专题汇集了发表于AI的系列研究，系统探讨了计算机视觉与图像处理在农业、医疗、工业、自动驾驶与媒体取证等多元场景中的技术突破与应用落地：从面部驱动正畸中的AI辅助诊断与治疗规划、基于轻量级CNN的AI生成图像检测，到自动驾驶车辆3D目标检测的多传感器融合综述；在垂直应用层面，涵盖了视觉Transformer优化灰霉病早期检测、棉铃与花朵识别的实时高精度模型、边缘-云框架下的牛只生物特征识别与健康分类，以及基于域随机化合成多模态数据集的手部实例分割。面向模型可信与可解释性，研究提出了基于CNN的光伏故障识别捷径学习多方法可解释性审计，并利用基于CLIP的多模态SigLIP-2视觉Transformer实现深度伪造检测与篡改区域定位。十项研究共同勾勒了计算机视觉与图像处理从感知工具向可解释、可部署、跨域智能系统演进的前沿图景。
1. AI and Face-Driven Orthodontics: A Scoping Review of Digital Advances in Diagnosis and Treatment Planning
人工智能与面部驱动正畸：诊断与治疗规划中数字化进展的范围综述
https://www.mdpi.com/2673-2688/5/1/9
Tomášik, J.; Zsoldos, M.; Oravcová, M.; Lifková, M.; Pavleová, G.; Strunga, M.; Thurzo, A. AI and Face-Driven Orthodontics: A Scoping Review of Digital Advances in Diagnosis and Treatment Planning.AI2024,5, 158-176.
2. Detection of AI-Generated Synthetic Images with a Lightweight CNN
使用轻量级卷积神经网络检测AI生成的合成图像
https://www.mdpi.com/2673-2688/5/3/76
Lokner Ladevic, A.; Kramberger, T.; Kramberger, R.; Vlahek, D. Detection of AI-Generated Synthetic Images with a Lightweight CNN.AI2024,5, 1575-1593.
3. Recent Advances in 3D Object Detection for Self-Driving Vehicles: A Survey
自动驾驶车辆3D目标检测的最新进展：综述
https://www.mdpi.com/2673-2688/5/3/61
Fawole, O.A.; Rawat, D.B. Recent Advances in 3D Object Detection for Self-Driving Vehicles: A Survey.AI2024,5, 1255-1285.
4. Vision Transformers in Optimization of AI-Based Early Detection of Botrytis cinerea
视觉Transformer在优化基于AI的灰霉病早期检测中的应用
https://www.mdpi.com/2673-2688/5/3/63
Christakakis, P.; Giakoumoglou, N.; Kapetas, D.; Tzovaras, D.; Pechlivani, E.-M. Vision Transformers in Optimization of AI-Based Early Detection of Botrytis cinerea.AI2024,5, 1301-1323.
5. A Comparison of Convolutional Neural Network Transfer Learning Regression Models for Remote Photoplethysmography Signal Estimation
用于远程光电容积描记信号估计的卷积神经网络迁移学习回归模型比较
https://www.mdpi.com/2673-2688/6/2/24
Sturekova, J.; Kamencay, P.; Sykora, P.; Hlavata, R. A Comparison of Convolutional Neural Network Transfer Learning Regression Models for Remote Photoplethysmography Signal Estimation.AI2025,6, 24.
6. RA-CottNet: A Real-Time High-Precision Deep Learning Model for Cotton Boll and Flower Recognition
RA-CottNet：一种用于棉铃和棉花花朵识别的实时高精度深度学习模型
https://www.mdpi.com/2673-2688/6/9/235
Wang, R.-F.; Qin, Y.-M.; Zhao, Y.-Y.; Xu, M.; Schardong, I.B.; Cui, K. RA-CottNet: A Real-Time High-Precision Deep Learning Model for Cotton Boll and Flower Recognition.AI2025,6, 235.
7. Dairy DigiD: An Edge-Cloud Framework for Real-Time Cattle Biometrics and Health Classification
Dairy DigiD：一种用于实时牛只生物特征识别与健康分类的边缘-云框架
https://www.mdpi.com/2673-2688/6/9/196
Mahato, S.; Neethirajan, S. Dairy DigiD: An Edge-Cloud Framework for Real-Time Cattle Biometrics and Health Classification.AI2025,6, 196.
8. HaDR: Hand Instance Segmentation Using a Synthetic Multimodal Dataset Based on Domain Randomization
HaDR：基于域随机化的合成多模态数据集用于手部实例分割
https://www.mdpi.com/2673-2688/7/2/72
Grushko, S.; Vysocký, A.; Chlebek, J. HaDR: Hand Instance Segmentation Using a Synthetic Multimodal Dataset Based on Domain Randomization.AI2026,7, 72.
9. Diagnosing Shortcut Learning in CNN-Based Photovoltaic Fault Recognition from RGB Images: A Multi-Method Explainability Audit
诊断基于CNN的光伏故障识别中RGB图像的捷径学习：一项多方法可解释性审计
https://www.mdpi.com/2673-2688/7/3/94
Diaconu, B.M. Diagnosing Shortcut Learning in CNN-Based Photovoltaic Fault Recognition from RGB Images: A Multi-Method Explainability Audit.AI2026,7, 94.
10. Deepfake Detection Using Multimodal CLIP-Based SigLIP-2 Vision Transformers
基于CLIP多模态SigLIP-2视觉Transformer的深度伪造检测
https://www.mdpi.com/2673-2688/7/3/115
Soundararajan, J.; Xu, D. Deepfake Detection Using Multimodal CLIP-Based SigLIP-2 Vision Transformers.AI2026,7, 115.
期刊介绍
主编：Prof. Dr. Kenji Suzuki, Tokyo Institute of Technology
AI（ISSN 2673-2688）是一个国际性、跨学科的开放获取英文学术期刊，聚焦人工智能领域的前沿研究，广泛覆盖机器学习、自然语言处理、智能机器人等所有AI子方向。期刊现已被ESCI（Web of Science）、Scopus和DOAJ等权威数据库收录，并展现出强劲的学术影响力：最新影响因子已达6.5，年增长30%，在JCR“计算机科学：跨学科应用”和“计算机科学：人工智能”两个领域中均位列Q1；CiteScore为7.3，2025年SCImago期刊排名（SJR）亦位于人工智能领域Q1。
2025 Impact Factor：6.5
2025 CiteScore：7.3
Time to First Decision：20.4 Days
Acceptance to Publication：5.6 Days
特别声明：本文转载仅仅是出于传播信息的需要，并不意味着代表本网站观点或证实其内容的真实性；如其他媒体、网站或个人从本网站转载使用，须保留本网站注明的“来源”，并自负版权等法律责任；作者如果不希望被转载或者联系转载稿费等事宜，请与我们接洽。
