Recent Advances in Object Detection and Computer Vision

Dear Colleagues,

The field of computer vision has witnessed a paradigm shift driven by the explosion of deep learning and the increasing demand for robust perception in complex, real-world environments. While traditional object detection and recognition systems have reached remarkable maturity in closed-set scenarios, transitioning these technologies into dynamic and unconstrained settings remains a significant hurdle. Modern applications—ranging from autonomous driving and industrial inspection to large-scale scene understanding—require models that not only "see" but also comprehend intricate relationships, handle data scarcity, and integrate heterogeneous information sources.

Currently, the research community is pivoting toward more holistic and resilient frameworks. This includes bridging the gap between multiple modalities to overcome the limitations of single-sensor systems and tackling the "long-tail" distribution of real-world data where rare but critical categories often go unrecognized. Furthermore, the evolution from 2D perception to high-fidelity 3D reconstruction and the enhancement of degraded visual inputs are becoming essential for comprehensive environmental modeling. In parallel, the shift toward open-vocabulary detection and the integration of structured knowledge through knowledge graphs are paving the way for more "intelligent" and explainable vision systems.

This Special Issue aims to provide a platform for researchers to present and disseminate their latest breakthroughs in object detection and advanced computer vision. We invite high-quality, original research and review articles that address both theoretical innovations and practical challenges in creating the next generation of visual perception systems.

Topics of interest include, but are not limited to, the following:

• Multimodal Object Detection: Fusion strategies for RGB, Sonar, LiDAR, thermal, and depth data to enhance detection robustness.
• Long-tail Distribution Learning: Innovative loss functions, sampling strategies, and architectures for long-tail classification and detection.
• 3D Scene Reconstruction: Advances in Neural Radiance Fields (NeRF), Gaussian Splatting, and multi-view geometry for high-precision modeling.
• Image Enhancement and Restoration: Low-light enhancement, de-hazing, and super-resolution techniques for improving downstream vision tasks.
• Object Detection in the Wild: Open-world and open-vocabulary detection, zero-shot learning, and adaptation to unconstrained environments.
• Industrial Defect Detection: High-precision anomaly detection, surface inspection, and few-shot learning for manufacturing quality control.
• CV-Enhanced Knowledge Graph Construction: Leveraging vision models for entity extraction, relation discovery, and multimodal knowledge reasoning.
• Cross-Domain Generalization: Domain adaptation and alignment techniques for transferring models across disparate visual domains.
• Benchmarking and Datasets: New large-scale datasets and evaluation metrics for complex computer vision tasks.
• Vision-Language Model Fine-tuning: Efficient fine-tuning and alignment techniques for large-scale vision-language models.

Dr. Wenyi Zhao
Dr. Wei Li
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. Electronics is an international peer-reviewed open access semimonthly 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 2400 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.