Motion-Centric Video Processing

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 15 December 2024 | Viewed by 674

Special Issue Editors


E-Mail Website
Guest Editor
School of Computing, The Australian National University, Canberra, Australia
Interests: action recognition in videos; anomaly detection; video image processing; one- and few-shot learning; deep learning; tensor learning; domain adaptation

E-Mail Website
Guest Editor
School of Elec Eng, Comp, and Math Sci, Curtin University, Perth, Australia
Interests: responsive AI / human centered computing: AI on human physiological/biometric data to predict internal states such as stress, depression, emotion veracity, doubt; responsible AI: a privacy by design approach to control private and personal data used by responsive AI; biologically inspired computing: neural networks, deep learning, fuzzy systems, evolutionary programming; deep learning for effects from images, video, and thermal data; neural networks for feature selection, rule extraction, explanations, architecture related to tasks, cascade correlation; fuzzy logic: fuzzy interpolation, fuzzy signatures; eye gaze inference; interactive evolutionary computation in new media or games, generation of art; natural and novel interfaces

E-Mail Website
Guest Editor
School of Computing, The Australian National University, Canberra, Australia
Interests: human action recognition; graph neural networks; human-centered computing

Special Issue Information

Dear Colleagues,

I am excited to introduce the scope and purpose of our upcoming MDPI open-access journal Electronics Special Issue, which aims to address the challenges and advancements in motion-centric video processing. This Special Issue will focus on the development and implementation of efficient and lightweight techniques to enhance video-based recognition, detection, and understanding systems in practical scenarios.

The primary focus of this Special Issue is to explore innovative approaches that can handle the complexities of motion-centric video processing. We aim to cover a broad scope of topics, including, but not limited to, the following:

Focus: Investigating novel methods for motion extraction, spatio-temporal feature learning, and video representation to improve the efficiency and effectiveness of video processing systems.

Scope: Addressing challenges such as scene understanding, human action recognition, anomaly detection, and other relevant applications within the realm of video processing.

Purpose: Providing a platform for researchers to present their latest findings, methodologies, and insights into motion-centric video processing. The goal is to foster the development of practical solutions that can be applied in real-world scenarios.

This Special Issue will complement the existing literature by offering fresh perspectives and innovative techniques in the field of video processing. By highlighting the importance of motion-centric approaches, we aim to bridge the gap between theoretical research and practical applications. Our contributions will build upon the foundation laid by previous studies, offering new insights and solutions to address the evolving challenges in this domain.

We invite submissions presenting new and original research on topics including, but not limited to, the following:

  1. Motion-centric video processing;
  2. Efficient video representation;
  3. Scene understanding;
  4. Human action recognition;
  5. Anomaly detection;
  6. Lightweight techniques (e.g., architectures, models, machine learning algorithms, etc.);
  7. LLMs on videos (e.g., foundation models, etc.);
  8. Practical applications (e.g., vision, language, audio, etc.).

This special issue is now open for submission. The deadline for manuscript submissions is 15 December 2024

Dr. Lei Wang
Prof. Dr. Tom Gedeon
Dr. Zhenyue Qin
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

  • motion extraction
  • spatio-temporal features
  • video representation
  • scene understanding
  • human action recognition
  • anomaly detection
  • optical flow
  • depth videos
  • skeleton sequences
  • lightweight models
  • machine learning
  • computer vision
  • large video foundation models
  • large language models (LLMs)
  • efficient motion data
  • video processing challenges
  • privacy
  • real-world applications

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.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

22 pages, 1698 KiB  
Article
Augmented Feature Diffusion on Sparsely Sampled Subgraph
by Xinyue Wu and Huilin Chen
Electronics 2024, 13(16), 3249; https://doi.org/10.3390/electronics13163249 - 15 Aug 2024
Viewed by 412
Abstract
Link prediction is a fundamental problem in graphs. Currently, SubGraph Representation Learning (SGRL) methods provide state-of-the-art solutions for link prediction by transforming the task into a graph classification problem. However, existing SGRL solutions suffer from high computational costs and lack scalability. In this [...] Read more.
Link prediction is a fundamental problem in graphs. Currently, SubGraph Representation Learning (SGRL) methods provide state-of-the-art solutions for link prediction by transforming the task into a graph classification problem. However, existing SGRL solutions suffer from high computational costs and lack scalability. In this paper, we propose a novel SGRL framework called Augmented Feature Diffusion on Sparsely Sampled Subgraph (AFD3S). The AFD3S first uses a conditional variational autoencoder to augment the local features of the input graph, effectively improving the expressive ability of downstream Graph Neural Networks. Then, based on a random walk strategy, sparsely sampled subgraphs are obtained from the target node pairs, reducing computational and storage overhead. Graph diffusion is then performed on the sampled subgraph to achieve specific weighting. Finally, the diffusion matrix of the subgraph and its augmented feature matrix are used for feature diffusion to obtain operator-level node representations as inputs for the SGRL-based link prediction. Feature diffusion effectively simulates the message-passing process, simplifying subgraph representation learning, thus accelerating the training and inference speed of subgraph learning. Our proposed AFD3S achieves optimal prediction performance on several benchmark datasets, with significantly reduced storage and computational costs. Full article
(This article belongs to the Special Issue Motion-Centric Video Processing)
Show Figures

Figure 1

Back to TopTop