Efficient Deep Learning for Vision-Based Sensing and Perception
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".
Deadline for manuscript submissions: 20 December 2026 | Viewed by 111
Special Issue Editor
Interests: computer vision; machine learning; artificial intelligence; software development in C++ and Python
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Deep learning has revolutionized our society in many areas but especially in the domain of vision-based sensing and perception. Hence, this MDPI Sensors Special Issue focuses on recent advances in efficient deep learning methods for vision-based sensing and perception systems. With the growing deployment of visual sensors in resource-constrained and real-world environments, there is an increasing need for models that achieve high accuracy while maintaining low computational, memory, and energy requirements. This Special Issue aims to bring together researchers and practitioners working on novel methods, algorithms, architectures, and system-level solutions that enable scalable, real-time, and reliable visual perception.
This Special Issue on efficient deep learning for vision-based sensing and perception is intended for researchers, engineers, and practitioners in computer vision, machine learning, embedded systems, robotics, and intelligent sensing, who are interested in bridging the gap between state-of-the-art deep learning and practical deployment in sensing and industry applications.
Original submissions from all areas related to efficient deep learning methods for vision-based sensing and perception are welcome. Topics of interest include, but are not limited to, the following ones.
Topics:
- Efficient deep neural network architectures for visual sensing;
- Model compression, pruning, quantization, and knowledge distillation;
- Vision-based perception on edge and embedded devices;
- Real-time object detection, tracking, and scene understanding;
- Multi-camera and distributed vision sensing systems;
- Energy-aware and hardware-efficient vision algorithms;
- Self-supervised, weakly supervised, and few-shot learning for visual sensing;
- Domain adaptation and robustness in real-world vision systems;
- Applications in smart cities, surveillance, autonomous systems, and human-centric sensing;
- Efficient semantic feature extraction for vision-based sensing;
- Compact and discriminative visual embeddings for perception tasks;
- Vision Transformers (ViTs) for resource-efficient sensing and perception;
- Efficient attention mechanisms and token reduction strategies;
- Cross-modal and vision–language embeddings for sensing applications;
- Lightweight adaptation of large vision–language models (VLMs);
- Efficient adaptation and fine-tuning of CLIP-related sensing tasks;
- Lightweight CLIP variants for embedded and edge vision systems;
- Vast applications of efficient deep learning for vision-based sensing and perception.
Prof. Dr. Bogusław Cyganek
Guest Editor
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. Sensors 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 2600 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.
Keywords
- deep learning
- neural networks
- visual transformers
- computer vision
- large vision–language models
- vision embedded systems
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
