New Trends in Computer Vision for Activity Recognition and 3D Human Pose Understanding
A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".
Deadline for manuscript submissions: 15 March 2026 | Viewed by 61
Special Issue Editors
Interests: computer vision; image processing; 3D modeling; deep learning/machine learning; meta-learning; human activity recognition; motion analysis
Interests: machine vision and image processing; 3D sensing and modeling; human motion capture and gesture analysis; tactile sensing and dexterous robotic manipulation; robots’ navigation; automation and intelligent manufacturing; computational intelligence
Interests: applied AI; machine intelligence, learning systems, neural networks, and biologically inspired computational models; data analytics; computational intelligence techniques for complex data and image processing; sensors and intelligent sensing; human–machine interfaces; multimodal sensor systems for data acquisition; 3D deformable object sensing, modeling, and manipulation; tactile and vision sensing and modeling for virtualized reality environments; selective and attention-based sensing and modeling
Special Issue Information
Dear Colleagues,
Activity recognition and 3D human pose estimation are two rapidly evolving fields in computer vision and artificial intelligence. This Special Issue aims to showcase recent advances and emerging trends in these areas, with an emphasis on technical innovation, diverse application scenarios, and pressing academic challenges. We invite the submission of original research that bridges cutting-edge deep learning algorithms with real-world use cases, security, virtual reality, human–computer interaction, healthcare, and more. This Special Issue aims to collate emerging strategies such as efficient lightweight models and privacy-aware solutions, managing data quality issues across sensing modalities, ensuring model generalizability across diverse contexts, and accurately interpreting subtle human gestures and movements, with the goal of fostering interdisciplinary collaboration and driving progress in human-centric vision research.
In recent years, we have seen significant advancements in the use of deep learning techniques for activity recognition and 3D pose estimation. Modern approaches leverage sophisticated network architectures and training strategies to improve accuracy, efficiency, and robustness.
Topics of interest for this Special Issue include, but are not limited to, the following:
- Deep Learning and Network Architectures;
- Multimodal and Multisensor Fusion;
- Lightweight and Efficient Models;
- Privacy-Preserving and Ethical AI;
- Self-Supervised and Generative Learning;
- Physics-Based and Hybrid Models;
- Practical Applications in Health, Surveillance, and Ambient Intelligence.
Dr. Ghazal Rouhafzay
Prof. Dr. Pierre Payeur
Dr. Ana-Maria Cretu
Dr. Éric Hervet
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 100 words) can be sent to the Editorial Office for announcement on this website.
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.
Keywords
- deep learning
- computer vision
- sensor fusion
- multimodal perception
- 3D human pose estimation
- action recognition
- gesture and motion analysis
- lightweight models
- privacy-preserving AI
- self-supervised learning
- physics-based and hybrid models
- healthcare and rehabilitation
- sports performance analysis
- surveillance and security
- human–robot interaction
- augmented reality
- ambient intelligence
- smart environments
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.
